[Feature][Refactor][P/D] Add MooncakeConnectorV2 by nwpu-zxr · Pull Request #14068 · vllm-project/vllm-ascend

nwpu-zxr · 2026-08-12T03:21:02Z

What this PR does / why we need it?

Add MooncakeConnectorV2. More information and RFC will be added later.

Does this PR introduce any user-facing change?

No.

How was this patch tested?

By CI.

vLLM main: vllm-project/vllm@b2f6858

gemini-code-assist · 2026-08-12T03:21:12Z

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refactors the Mooncake KV transfer connector to improve modularity and support a pull-based transfer mechanism. By introducing dedicated base classes for schedulers and workers, the implementation cleanly separates control plane logic from data plane transfer operations. This change enhances maintainability and provides a foundation for future connector types.

Highlights

Mooncake Connector Refactor: Introduced a new modular architecture for Mooncake KV transfer connectors, separating scheduler and worker logic into dedicated base classes and implementations.
Pull-based Transfer Implementation: Implemented the pull-based connector logic, including scheduler-side control threads and worker-side data transfer threads for efficient KV cache loading.
Metadata and Utilities: Added comprehensive metadata structures and utility functions to handle KV cache registration, address mapping, and ZMQ-based communication between scheduler and workers.

New Features

🧠 You can now enable Memory (public preview) to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize the Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counterproductive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

github-actions · 2026-08-12T03:22:28Z

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

A PR should do only one thing, smaller PRs enable faster reviews.
Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

gemini-code-assist

Code Review

Suggested PR Title:

[Ops][Feature] Implement Mooncake KV transfer connectors for Ascend

Suggested PR Summary:

### What this PR does / why we need it?
This PR implements the Mooncake KV transfer connectors for the Ascend backend, enabling direct device-to-device (D2D) KV cache transfers. It introduces base and pull-based implementations for both schedulers and workers, along with metadata, statistics, and Prometheus metrics tracking.

Several critical issues were identified during the review:
- In `pull_worker.py`, the source and destination address lists (`src_list` and `dst_list`) are swapped in multiple places during pull transfers, which would cause severe runtime crashes or memory corruption.
- The retry logic in `utils.py` for `zmq.REQ` sockets is broken because ZeroMQ REQ sockets cannot simply retry `send`/`recv` on failure without being recreated or using a `DEALER` socket.
- Type annotations and comparisons for `remote_num_kv_heads` in `pull_worker.py` can lead to a `TypeError` if it is `None`.
- Prompt length calculations in `pull_scheduler.py` rely on `prompt_token_ids`, which breaks embedding-based requests where token IDs are `None`.
- A potential `IndexError` exists in `base_scheduler.py` when popping from `_all_token_ids` if it is empty.

### Does this PR introduce _any_ user-facing change?
Yes, it introduces the Mooncake KV transfer connector for Ascend, allowing users to configure and use Mooncake for KV cache transfers.

### How was this patch tested?
No tests were added in this PR. It is recommended to add unit and integration tests for the Mooncake scheduler and worker transfer paths, particularly covering the edge cases identified in the review (e.g., embedding-based requests, empty token IDs, and connection retries).

gemini-code-assist · 2026-08-12T03:23:30Z

+                            src_list.append(local_block_addr + local_inner_offset)
+                            dst_list.append(remote_block_addr + remote_inner_offset)


In MooncakePullRecvingThread, which runs on the D-side (consumer), the local memory is the destination and the remote memory is the source. Therefore, src_list (source) should contain the remote addresses, and dst_list (destination) should contain the local addresses. Currently, they are swapped here, which will cause the transfer engine to read from local memory and write to remote memory, leading to severe runtime crashes or memory corruption.

src_list.append(remote_block_addr + remote_inner_offset)\n dst_list.append(local_block_addr + local_inner_offset)

gemini-code-assist · 2026-08-12T03:23:30Z

+                            src_list.append(local_base_addr + local_block_id * local_block_stride)
+                            dst_list.append(remote_base_addr + remote_block_id * remote_block_stride)


In MooncakePullRecvingThread, which runs on the D-side (consumer), the local memory is the destination and the remote memory is the source. Therefore, src_list (source) should contain the remote addresses, and dst_list (destination) should contain the local addresses. Currently, they are swapped here, which will cause the transfer engine to read from local memory and write to remote memory, leading to severe runtime crashes or memory corruption.

src_list.append(remote_base_addr + remote_block_id * remote_block_stride)\n dst_list.append(local_base_addr + local_block_id * local_block_stride)

gemini-code-assist · 2026-08-12T03:23:30Z

+                        src_list.append(local_base_addr + local_block_id * local_block_stride + local_inner_offset)
+                        dst_list.append(remote_base_addr + remote_block_id * remote_block_stride + remote_inner_offset)


In MooncakePullRecvingThread, which runs on the D-side (consumer), the local memory is the destination and the remote memory is the source. Therefore, src_list (source) should contain the remote addresses, and dst_list (destination) should contain the local addresses. Currently, they are swapped here, which will cause the transfer engine to read from local memory and write to remote memory, leading to severe runtime crashes or memory corruption.

src_list.append(remote_base_addr + remote_block_id * remote_block_stride + remote_inner_offset)\n dst_list.append(local_base_addr + local_block_id * local_block_stride + local_inner_offset)

gemini-code-assist · 2026-08-12T03:23:30Z

+def ensure_zmq_send(
+    socket: zmq.Socket,  # type: ignore
+    data: bytes,
+    path: str,
+    max_retries: int = 3,
+):
+    retries_left = max_retries
+    while True:
+        try:
+            socket.send(data)
+            return
+        except zmq.ZMQError as e:  # type: ignore
+            retries_left -= 1
+            if retries_left > 0:
+                logger.warning("Send failed. error=%s, attempts_left=%d. ", e, retries_left)
+                time.sleep(0.1)
+            else:
+                logger.error("Send failed after all retries. error=%s. ", e)
+                raise RuntimeError(f"Failed to send data to {path} after {max_retries} retries: {e}")
+
+
+def ensure_zmq_recv(
+    socket: zmq.Socket,  # type: ignore
+    path: str,
+    max_retries: int = 3,
+) -> bytes:
+    retries_left = max_retries
+    while True:
+        try:
+            return socket.recv()
+        except zmq.ZMQError as e:  # type: ignore
+            retries_left -= 1
+            if retries_left > 0:
+                logger.warning("Receive failed. error=%s, attempts_left=%d. ", e, retries_left)
+                time.sleep(0.1)
+            else:
+                logger.error("Receive failed after all retries. source=%s, error=%s. ", path, e)
+                raise RuntimeError(f"Failed to receive data after {max_retries} retries: {e}")
+


The retry logic in ensure_zmq_send and ensure_zmq_recv is broken for zmq.REQ sockets. In ZeroMQ, a REQ socket strictly enforces a send-receive state machine. If a recv() or send() times out or fails, the socket enters an exceptional state and any subsequent calls on the same socket will immediately fail with EFSM (state flow error). Therefore, simply retrying recv() or send() in a loop on the same socket will not work and will just repeatedly fail. The socket must be closed and recreated to retry, or a zmq.DEALER socket should be used instead.

gemini-code-assist · 2026-08-12T03:23:30Z

+    def _infer_total_num_kv_heads(
+        self,
+        local_num_kv_heads: int,
+        remote_num_kv_heads: int | None,


In _infer_total_num_kv_heads, remote_num_kv_heads is typed as int | None. However, the code performs comparisons like max(local_num_kv_heads, remote_num_kv_heads) and remote_num_kv_heads > 1 without checking if it is None. If remote_num_kv_heads is None, this will raise a TypeError and crash the worker. Since it is always an int in practice, the type annotation should be updated to int.

Suggested change

remote_num_kv_heads: int | None,

remote_num_kv_heads: int,

gemini-code-assist · 2026-08-12T03:23:30Z

+            token_ids = request.prompt_token_ids or []
+            actual = self._state_prefill_token_count(len(token_ids))


The code uses len(request.prompt_token_ids or []) to determine the prompt length. However, if the request uses prompt embeddings instead of token IDs, request.prompt_token_ids will be None, resulting in a prompt length of 0 even though request.num_prompt_tokens is greater than 0. This will break KV transfer for embedding-based requests. request.num_prompt_tokens should be used instead.

Suggested change

token_ids = request.prompt_token_ids or []

actual = self._state_prefill_token_count(len(token_ids))

actual = self._state_prefill_token_count(request.num_prompt_tokens)

gemini-code-assist · 2026-08-12T03:23:30Z

+        prompt_token_ids = request.prompt_token_ids or []
+        prompt_len = len(prompt_token_ids)


The code uses len(request.prompt_token_ids or []) to determine the prompt length. However, if the request uses prompt embeddings instead of token IDs, request.prompt_token_ids will be None, resulting in a prompt length of 0 even though request.num_prompt_tokens is greater than 0. This will break KV transfer for embedding-based requests. request.num_prompt_tokens should be used instead.

Suggested change

prompt_token_ids = request.prompt_token_ids or []

prompt_len = len(prompt_token_ids)

prompt_len = request.num_prompt_tokens

gemini-code-assist · 2026-08-12T03:23:30Z

+        else:
+            return
+
+        request._all_token_ids.pop()


In _truncate_request_for_prefill, request._all_token_ids.pop() is called. If prompt_token_ids is None (e.g., when using prompt embeddings), _all_token_ids might be empty, and calling pop() on it will raise an IndexError and crash the engine. This should be guarded with an if request._all_token_ids: check.

if request._all_token_ids:\n request._all_token_ids.pop()

…t#14068) Squashed from the 40 commits in upstream PR vllm-project#14068 and rebased onto 26190b4.

wangxiaoteng888 · 2026-09-02T01:40:08Z

+
+        logger.info("Initializing Mooncake Scheduler %s", engine_id)
+
+    def _needs_prefill_token_truncation(self) -> bool:


Is this method necessary?

Yes. For state model like Qwen3.5 or DSV4, it's necessary to truncate the last token.

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

Patch loaded Mooncake modules directly instead of resolving dotted paths through parent packages that other CPU tests can replace. Cover a detached kv_p2p parent attribute in the socket context test. Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>

### What this PR does / why we need it? Add `MooncakeConnectorV2`. More information and RFC will be added later. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? By CI. - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com> Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com> Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com>

### What this PR does / why we need it? #### Summary Upgrade the verified vLLM main revision while retaining v0.28.0 compatibility. | Input | Exact revision | |---|---| | Previous vLLM main | `b2f685834a6456197e7033966fdef52a23f1abcd` | | Target vLLM main | `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` (September 9 target; unchanged by this revision) | | Retained release | `v0.28.0` / `2cf0a6915ce544dc493a0990f2ea38d81601128a` | | Current Ascend PR base | `1b1709b9227ad3e0db2d82b9231c4962919b86f5` | | Reviewed PR head | `225f7cfdbf1c479798643a7d70a7e2031e5466f2` | Current PR-wide diff: **61 files, +819/-418**. The numbered inventory below matches the current GitHub changed-file list one-to-one. Removed changes and historical commit-by-commit progress are not part of this inventory. #### Scope and version handling - Adapt the exact upstream contracts linked below. Where main and release differ, select the lane with `vllm_version_is("0.28.0")`; share logic where both contracts match. - The owner also included baseline dual-version compatibility gaps. In particular, #51031's KV/kernel block-size split predates this main upgrade. Newly merged Ascend consumers from [#14068][ascmoon], [#14699][ascextract] and [#15969][ascpcp] require compatibility handling; they are not mislabeled as newly introduced vLLM breaks. - **No workflow changes remain in this PR.** CPU UT uses the inherited single-main configuration. The existing `main2main` label continues to select main/tag NPU validation. - Keep existing tests and necessary test adaptations; do not add guard-test files or cases. On release only, skip the three unsupported MRV2 extract-hidden-states cases at the owner's request, rather than asserting an initialization error. V1 on both versions and MRV2 on main remain enabled. - The existing owner-authorized release SFA PCP precision exclusion remains a temporary exception, not a precision fix or passing result. The rebased Ascend main now inherits [#16306](#16306), which temporarily skips DSpark PCP. This PR does not modify that test file or add the skip. A green CI with this inherited skip is not an actual DSpark pass; the independent precision investigation/fix remains outside this PR. - No new patch file is added. This does not add DBO, CUDA Triton attention, NPU ReplaySSM or release MRV2 extract-hidden-states support. #### File-by-file changes and upstream evidence Lane key: **M** = main, **R** = release, **B** = both (possibly version-selected); **T** = test adaptation; **E** = explicitly authorized exception. Upstream links for baseline compatibility or test exclusions document the relevant contract, not a claim that this upgrade introduced the issue. ##### Dependency pin (1 file) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 1. `.github/vllm-main-verified.commit` | M | Advance the verified main pin from b2f6858 to a97dacb; the release tag is unchanged. | [exact upgrade range][range] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Device test adaptations (4 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 2. `tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_compute_slot_mapping.py` | B/T | Keep the inherited windowed-kernel test inputs. Main passes separate KV/kernel sizes and enablement to its reference kernel. Release lacks that reference ABI: first derive CP-local positions, then invoke the release CP=1 physical-slot reference and mask non-local tokens. Adapt the existing out-buffer fixture; add no cases. | [#53896 ABI][uniform]; [main source][blockM]; [release source][blockR]; [Ascend #16120][ascwindow] | 10 actual-source CPU simulations passed, including both lanes; selected NPU CI passed; coverage limits in the testing section | | 3. `tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py` | R/E | Temporarily skip only test_dsv3_2_sfa_pcp_model_runner_v2_graph_accuracy on v0.28.0 at the owner's request. Keep main and other cases unchanged; this is NOT a precision fix or an upstream-break claim. | [baseline test being isolated][sfatest] | Owner-authorized precision exception; unresolved | | 4. `tests/e2e/pull_request/one_card/spec_decode/test_extract_hidden_states.py` | R/T | Skip only the three existing cases with use_v2_model_runner=True on v0.28.0, whose upstream configuration rejects extract_hidden_states with MRV2. Keep all V1 cases and main MRV2 execution unchanged; no rejection-contract guard is added. | [#49811 implementation][extract]; [release rejection][configR]; [Ascend #14699 cases][ascextract] | Four source-isolated version/runner combinations and Ruff passed; selected device CI passed; coverage limits in the testing section | | 5. `tests/e2e/pull_request/one_card/test_gumbel_sampling.py` | B/T | Adapt the existing Gumbel tests to each lane's signature and installed implementation identity. | [#54282 Gumbel signature][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Existing CPU test adaptations (24 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 6. `tests/ut/core/test_dyntra_lb_scheduler.py` | B/T | Build the actual SchedulerOutput fields for each lane; verify boundary offers only on main while retaining connector/EC metadata checks. This is fixture compatibility, not new Dyntra behavior. | [#51358 scheduler output][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 7. `tests/ut/core/test_recompute_scheduler.py` | B/T | Adapt the existing scheduler test's drain fixture and assertion to main boundary offers versus release partial-tail offers. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 8. `tests/ut/core/test_scheduler_connector_block_state.py` | B/T | Verify Recompute/Dyntra handoff using real lane-specific output fields and cleared scheduler-local state, not only dispatch mocks. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 9. `tests/ut/distributed/ascend_store/test_pool_worker.py` | B/T | Use torch.float32 in the Mamba spec fixture; uniformity/page-size evaluation reaches get_dtype_size and cannot consume the old NumPy dtype. | [#53896][uniform]; [spec definition][cacheM] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 10. `tests/ut/kv_offload/mooncake_v2/helpers.py` | B/T | Add a real KVCacheTensor fixture builder: release shared_by/block-stride/offset fields versus main layers/layer-stride fields. | [#51718 descriptor][layout]; [Ascend #14068 consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 11. `tests/ut/kv_offload/mooncake_v2/test_base_worker.py` | B/T | Use the real descriptor helper while retaining ordering, packed-view, SFA virtual-block and invalid-input assertions. | [#51718][layout]; [Ascend #14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 12. `tests/ut/kv_offload/mooncake_v2/test_utils.py` | B/T | Replace main-shaped descriptor stand-ins with real lane descriptors; preserve storage deduplication, independence and alignment checks. | [#51718][layout]; [Ascend #14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 13. `tests/ut/kv_offload/test_native_cpu_offload.py` | B/T | Supply data_parallel_size and data_parallel_rank_local in both fixtures: both pinned versions read them. Correct a false release assumption without changing offload behavior. | [main config][offloadM]; [release config][offloadR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 14. `tests/ut/models/test_deepseek_v4_vision_preprocess.py` | B/T | Give _StubInfo and its context a working shared tokenizer so the new processing-info path is tested without an incomplete mock. | [#54886 processor contract][vision] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 15. `tests/ut/models/test_glm5next_kv_cache.py` | B/T | Assert 16 physical storage rows through get_storage_block_size rather than main's nullable raw field; retain the new GLM architecture and its tests. | [#53906][storage]; [Ascend #15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 16. `tests/ut/ops/test_routed_experts.py` | B/T | Initialize quant_method.moe_kernel in both fixtures because expert_map already reads it on release too; no production MoE change. | [main expert_map][expertsM]; [release expert_map][expertsR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 17. `tests/ut/patch/platform/test_deepseek_v4_thinking.py` | B/T | Assert the actual reasoning-mode mapping on both pinned tokenizers; remove false release-only expectations while retaining all eight cases. | [main tokenizer][thinkingM]; [release tokenizer][thinkingR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 18. `tests/ut/patch/platform/test_patch_mamba_block_aligned_split.py` | B/T | Supply the common use_eagle_block_drop fixture field and main-only mamba_fine_grained_prefix_cache=False, preserving current indexer configuration. | [#53388 scheduler][schedfixture]; [#53945][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 19. `tests/ut/patch/platform/test_patch_structured_output.py` | B/T | Provide actual request/stop-token fields and validation exceptions on both lanes; retain the {2} stop-token payload and backend-locking assertions. | [main grammar creation][grammarM]; [release grammar creation][grammarR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 20. `tests/ut/patch/platform/test_patch_use_v2_model_runner.py` | B/T | Adapt the existing V1 helper test to the installed lane. | [main configuration][configM]; [release configuration][configR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 21. `tests/ut/patch/platform/test_prefix_cache_cp_patches.py` | B/T | Use the version-aware max-layers helper in the existing shared-tuple planner assertion. | [#53614][eagle]; [#53906][storage]; [#53896][packed] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 22. `tests/ut/patch/worker/test_patch_mamba_utils_uniform_groups.py` | B/T | Verify release's Ascend uniform-group override and main's upstream spec-keyed dictionary/MambaCopyBuffers contract. | [#53896][mamba]; [both-lane source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 23. `tests/ut/spec_decode/test_extract_hidden_states_proposer.py` | B/T | Create CPU buffers without pinned memory on both lanes instead of patching a PIN_MEMORY symbol absent from release; retain proposer behavior assertions. | [main proposer][proposerM]; [release proposer][proposerR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 24. `tests/ut/test_compressed_prefix_cache.py` | B/T | Use physical storage rows and pass replay_boundary to the three real manager calls only on main; retain all cache/hash assertions. | [#53906][storage]; [#53945 cache_blocks][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 25. `tests/ut/worker/test_attn_utils_v2.py` | B/T | Adapt existing storage/binding fixtures and the expected hidden-state cache layout to each lane. | [#53906][storage]; [#52506][bind]; [#51718 hidden-state path][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 26. `tests/ut/worker/test_extract_hidden_states_speculator_v2.py` | B/T | Run main's extract-hidden-states speculator tests only where that module exists; explicitly assert release dispatch raises NotImplementedError before import. | [#49811][extract]; [Ascend #14699][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 27. `tests/ut/worker/test_model_runner_v1.py` | B/T | Mock the version-aware Ascend Mamba copy-function producer in the real V1 runner fixture. | [#53896][mamba] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 28. `tests/ut/worker/test_model_runner_v2.py` | B/T | Adapt existing profiling/dummy-call kwargs and PCP buffer access to each lane. Preserve original test inputs. | [#54436][input]; [#52506][dummy]; [#53515][pcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 29. `tests/ut/worker/test_pcp_manager_v2.py` | B/T | Construct main ExecuteModelState with cudagraph_stats and other required current fields; omit fields absent from release. | [#52358 ExecuteModelState][stats] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Runtime adaptations (32 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 30. `vllm_ascend/_310p/worker/v2/block_table.py` | B | Accept and validate optional per-group slot enablement; write PAD for disabled groups in the 310P-owned buffers on both lanes. | [#53896 BlockTables][uniform] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 31. `vllm_ascend/_310p/worker/v2/model_runner.py` | B | Retain release InputBatch max_seq_len_np; forward the shared dummy-state flag; gate main-only circular specs and derive physical storage rows. | [#54436][input]; [#52506][dummy]; [#53896][uniform]; [#53906][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 32. `vllm_ascend/_310p/worker/v2/model_state.py` | B | Forward ubatch_id through the Ascend parent MRO; preserve the existing no-DBO limitation. | [#50945][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 33. `vllm_ascend/attention/context_parallel/common_cp.py` | B | Explicitly declare supports_dcp=True only on the mixin whose implementations already perform DCP, because upstream now defaults to False. | [#55780 capability default][dcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 34. `vllm_ascend/attention/context_parallel/dsa_cp.py` | B | Use get_storage_block_size for DSA CP physical cache geometry instead of directly reading the version-dependent spec field. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 35. `vllm_ascend/attention/dsa_v1.py` | B | Use the same physical-row helper in DSA attention cache geometry; preserve existing attention behavior. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 36. `vllm_ascend/core/kv_cache_interface.py` | B | Keep release's derived storage property without overriding main's optional dataclass field; centralize physical-row derivation, including UniformTypeKVCacheSpecs. | [#53906][storage]; [#51718 spec fields][layout] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 37. `vllm_ascend/core/recompute_scheduler.py` | B | Explicitly separate release producer partial-tail handoff from main boundary snapshots and scheduler-local connector state. Pass CoW copy tasks and EC manager metadata on both lanes: both pins define these fields. Keep CoW lifetime and scheduling policy unchanged. | [#51358 handoff][boundary]; [main producer][schedM]; [release producer][schedR]; [main fields][schedoutM]; [release fields][schedoutR] | Source reviewed; 8 isolated output cases and local formatting passed; selected current-head CI passed; coverage limits in the testing section | | 38. `vllm_ascend/distributed/device_communicators/npu_communicator.py` | B | Initialize fi_pcie_ipc_ar_comm=None because new upstream cleanup/communication code reads it; NPU does not create the CUDA communicator. | [#53576 reader][ipc] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 39. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/base_worker.py` | B | Use the existing version-aware get_kv_cache_tensor_layers helper instead of main-only .layers when registering Mooncake cache views. | [#51718 descriptor][layout]; [Ascend #14068 new consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 40. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/utils.py` | B | Use that same layer helper when collecting/deduplicating physical cache storage; preserve packed-layout semantics. | [#51718 descriptor][layout]; [Ascend #14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 41. `vllm_ascend/models/deepseek_v4/model.py` | B | Advertise the already implemented auxiliary-state-over-PP capability and expose Ascend's existing pp_transport_aux_hidden_states_ prefix to the upstream relay; release safely retains the declarations. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 42. `vllm_ascend/models/minimax_m3/minimax_m3.py` | B | Align existing auxiliary hidden-state PP capability and transport prefix with the new upstream interface, without adding a new model feature. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 43. `vllm_ascend/ops/kimi_mla.py` | M | Relocate the existing concrete Kimi MLA replacement into a lightweight ops module; preserve Ascend-first double inheritance for OOT initialization and forward. No model-module registration side effect. | [#52494 concrete caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated dispatch/MRO checks and Ruff passed; selected current-head CI passed; coverage limits in the testing section | | 44. `vllm_ascend/ops/rel_pos_attention.py` | B | Delete the constructor that only forwarded super incorrectly; inherit each lane's exact upstream signature/initialization, including use_triton_attention. NPU forward is unchanged. | [#55629 constructor/caller][relpos] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 45. `vllm_ascend/ops/triton/v2/block_table/compute_slot_mappings.py` | M | Add only the version-selected disabled-group PAD path. The inherited base now already implements separate KV/kernel addressing with a bounded window; preserve that algorithm, rather than restoring the old full-row staging/direct-load paths. | [#53896 enablement][uniform]; [Ascend #16120 inherited mapping][ascwindow] | Source diff verified: only enablement arguments and disabled-group path differ from base; CPU simulations passed; selected NPU CI passed; coverage limits in the testing section | | 46. `vllm_ascend/patch/platform/patch_kv_cache_coordinator.py` | M | Forward drop_eagle_checkpoint_block through the CP coordinator only on main; retain release's older call contract. | [#53614 coordinator][eagle] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 47. `vllm_ascend/patch/platform/patch_kv_cache_utils.py` | B | Bind main's live _get_packed_kv_cache_groups and matching max-layers helper; retain release's old grouping hooks and base GLM/Kimi grouping fixes. | [#53896 planner hooks][packed]; [Ascend #15913 architecture][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 48. `vllm_ascend/patch/platform/patch_use_v2_model_runner.py` | B | On release, override only the GPU-specific non-MLA PCP restriction already supported by Ascend; keep all other config rejections. Select the V1-helper patch by version. This is baseline compatibility, not a newly introduced upstream break. | [main config][configM]; [release config][configR]; [Ascend PCP consumer][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 49. `vllm_ascend/patch/worker/patch_bind_kv_cache.py` | B | Accept kv_cache_groups, retain stable layer binding and call share_replayssm_ring_trackers only on main after binding. Do not claim new NPU ReplaySSM support. | [#52506 binding/ring metadata][bind] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 50. `vllm_ascend/patch/worker/patch_mamba_utils.py` | B | Keep release tuple grouping/copy functions and uniform-group override; on main preserve upstream spec-keyed groups and select copy functions by mamba_type in each consumer. | [#53896 grouping][mamba]; [main source][mambasrcM]; [release source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 51. `vllm_ascend/patch/worker/patch_v2/patch_dspark.py` | B | Gate old module-level get_pp_group/_should_share bindings versus main's local imports. Remove obsolete temporary EP-config mutation now that upstream preserves target settings; retain quantization inheritance, PP guard restoration and the original target weight-attribute guard. | [#50514 bindings][dspp]; [#55472 config preservation][dspark] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 52. `vllm_ascend/utils.py` | M | Add the concrete Kimi wrapper mapping to the existing central custom-op registration under an explicit main-only version gate; retain the shared one-time guard and generic release mapping. | [#52494 caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated main/release import, mapping and repeat-call checks passed; selected current-head CI passed; coverage limits in the testing section | | 53. `vllm_ascend/worker/model_runner_v1.py` | B | Produce the lane-correct Mamba copy-function container and use physical storage rows in cache views, preserving the rebased per-layer attention-backend dispatch. | [#53896 V1 producer][producer]; [copy consumer][mamba]; [#53906][storage]; [Ascend #15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 54. `vllm_ascend/worker/v2/attn_utils.py` | B | Allocate hidden-state views in release [B,N,H,C] versus main [B,H,N,C] order after removal of the old shape hook; honor padded page size. | [#51718 hidden-state layout][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 55. `vllm_ascend/worker/v2/block_table.py` | B | Version-gate the parent enablement argument and normalize release KV/kernel size tensors at startup and wake-up. Preserve the inherited window sizing and launch configuration, forwarding enablement only on main. | [#53896][uniform]; [#51031][slot]; [main fields][blockM]; [release fields][blockR]; [Ascend #16120][ascwindow] | Both-lane actual-source output/padding simulations and Ruff passed; selected NPU CI passed; coverage limits in the testing section | | 56. `vllm_ascend/worker/v2/model_runner.py` | B | Install the existing combined-broadcast patch only on release; main inherits upstream separate PP draft receive/update/broadcast. Retain release InputBatch arguments and dummy-state/PCP buffer adaptations required by the new Ascend override. | [#50514][pp]; [#54436][input]; [#52506][dummy]; [Ascend #15969 new override][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 57. `vllm_ascend/worker/v2/model_states/default.py` | B | Accept upstream's optional ubatch_id in prepare_attn, defaulting to zero; keep explicit rejection of unsupported DBO/nonzero microbatches. | [#50945 default model state][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 58. `vllm_ascend/worker/v2/model_states/mamba_hybrid.py` | B | Apply the same prepare_attn signature contract to Mamba hybrid state, preserving the no-DBO guard. | [#50945 Mamba state][ubatchm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 59. `vllm_ascend/worker/v2/pcp_manager.py` | B | Use the already-owned _input_buffers with an explicit non-None assertion instead of a main-only convenience property; this adapts the PCP consumer newly added to the Ascend base. | [#53515 buffer ownership][pcp]; [Ascend #15969][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 60. `vllm_ascend/worker/v2/sample/gumbel.py` | B | Select exact public signatures: release's positional logits_cache versus main's required is_drafting before logits_cache. Forward into a shared internal implementation while preserving existing salt, stride, temperature and cache behavior. | [#54282 positional ABI][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 61. `vllm_ascend/worker/v2/spec_decode/__init__.py` | B | Reject release extract-hidden-states MRV2 dispatch explicitly before importing the main-only module; keep main's supported implementation. Do not backport the feature or merely hide collection errors. | [#49811 speculator][extract]; [Ascend #14699 new dispatch][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | #### Interface review and limitations The completed b2f6858-to-a97dacb interface report used Ascend baseline `9dfdd529e9bec72d452ecac22d4c512332323a5f`. Its findings were source-reviewed. It is reused at the owner's request; no expensive analyzer rerun is performed for this revision. That report does not automatically cover later rebased Ascend consumers. Those adaptations are linked individually above. The selected current-head integration suite passed; this does not establish exhaustive regression freedom. The release SFA exclusion and inherited upstream DSpark skip remain disclosed limitations; successful required checks will not establish DSpark precision recovery. ### Does this PR introduce _any_ user-facing change? Advance the verified main dependency while preserving supported v0.28.0 behavior through explicit version handling. The release-only unsupported-feature skip changes test reporting to SKIPPED; it does not backport MRV2 extract-hidden-states support or change model execution. ### How was this patch tested? - **Versions:** vLLM main `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` and release `v0.28.0`. NPU CI covers both lanes; CPU UT uses main only. - **CI:** [E2E run 34592721264](https://github.com/vllm-project/vllm-ascend/actions/runs/34592721264) passed on attempt 2 for PR head `225f7cfdb`. This is a rerun success, not a precision-fix claim. - **Coverage limits:** the inherited DSpark PCP skip (#16306), owner-authorized release SFA PCP exclusion, and three unsupported release MRV2 extract-hidden-states skips remain. Passing CI does not validate these excluded cases or all PP topologies. - **Local checks:** Ruff lint/format and `git diff --check` passed. Earlier source-isolated CPU checks are noted in the file table; no local NPU or full installed-vLLM validation is claimed. Full `bash format.sh ci` was unavailable on Windows. [slot]: https://github.com/vllm-project/vllm/pull/51031/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [uniform]: https://github.com/vllm-project/vllm/pull/53896/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [mamba]: https://github.com/vllm-project/vllm/pull/53896/files#diff-8ab86225fa08e9a6700851191abcb3f4f8b0bba40e97a82aad700d7a23a4d7ec [packed]: https://github.com/vllm-project/vllm/pull/53896/files#diff-fb2b41380ca86adbba904aff40b18a0815beb73c1198818912e71723383ab604 [storage]: https://github.com/vllm-project/vllm/pull/53906/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [layout]: https://github.com/vllm-project/vllm/pull/51718/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [hidden]: https://github.com/vllm-project/vllm/pull/51718/files#diff-57af80f3ae4b519ad1ac9d1338716420aed243a8f13d652a122ea4661e93708b [boundary]: https://github.com/vllm-project/vllm/pull/51358/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [ipc]: https://github.com/vllm-project/vllm/pull/53576/files#diff-cf486d32b11454e89103000ac0f9a93ee1ccbb8983c02e794b734a65301cd98b [vision]: https://github.com/vllm-project/vllm/pull/54886/files#diff-740d0a4b454d681455df7c9f56361deaafa7a5baaa9dce45e7fa0aefec3e8cbd [kimi]: https://github.com/vllm-project/vllm/pull/52494/files#diff-49368b83ccd7bf5f68204323e211a87440e53b608f5ecf91ff25d4832535b1b9 [kimiwrap]: https://github.com/vllm-project/vllm/pull/52494/files#diff-aad295e6de3607a46cea22f9f1cca768d4937dc5e1d3ca58105513358ed4e4c1 [dcp]: https://github.com/vllm-project/vllm/pull/55780/files#diff-bdb2df4662d59d54517931b86406644ee1e0c33cb3e00afac078d2a9aa550200 [relpos]: https://github.com/vllm-project/vllm/pull/55629/files#diff-53dffba908ca88d6f312c7e27606f8f6fa11fb476e279efa11d712576809e1dd [eagle]: https://github.com/vllm-project/vllm/pull/53614/files#diff-43875c71daa893ef7567e21633d9988c2baf95bef61e3a334a6d584d6444d725 [replay]: https://github.com/vllm-project/vllm/pull/53945/files#diff-97c184a680b7a4bd7d58b11aa0073706533cc887d990eddb98469e7374025ab3 [bind]: https://github.com/vllm-project/vllm/pull/52506/files#diff-645d58630d5acf3a0b07226bfef1e890a584c32502ab97c3d4642070f39a783c [dummy]: https://github.com/vllm-project/vllm/pull/52506/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [pp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-8330021c29feb32718335218ea994b6a770dd182a94b1baeacb7f7f42214afb7 [aux]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2ae789d702f81147ec584f3c0077aa3dedb6ebd424320dc607a44b86e3780874 [dspark]: https://github.com/vllm-project/vllm/pull/55472/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [dspp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [ubatch]: https://github.com/vllm-project/vllm/pull/50945/files#diff-aa6dbff87b81bae23ded2803a01a8c4913fceb6fe39c6d9423a20ad4b89859be [ubatchm]: https://github.com/vllm-project/vllm/pull/50945/files#diff-d6ed06f4278c0f7cd58e0eae8a019b484fba760424e9604284b3529843ba2384 [input]: https://github.com/vllm-project/vllm/pull/54436/files#diff-106f39c08266f186830bb8fcd7fb1df35c0aaa5fd0ac5c17aac64aeddee48902 [pcp]: https://github.com/vllm-project/vllm/pull/53515/files#diff-45dad5fe975c2ec8d02124fa65579cf11bfe9169a94217ceae1de0ea29518127 [gumbel]: https://github.com/vllm-project/vllm/pull/54282/files#diff-02f7c5a06a2d23d544a07d57af16c7ffb74886469c8844385f51a719e329e6b8 [extract]: https://github.com/vllm-project/vllm/pull/49811/files#diff-b13061cd1be0bc80aaa9fce208fe9128aaaad25b3832c5f1693da1d4e8263f5e [schedfixture]: https://github.com/vllm-project/vllm/pull/53388/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [stats]: https://github.com/vllm-project/vllm/pull/52358/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [offloadM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_offload/config.py [offloadR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/kv_offload/config.py [expertsM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/model_executor/layers/fused_moe/routed_experts.py [expertsR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/model_executor/layers/fused_moe/routed_experts.py [thinkingM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/tokenizers/deepseek_v4.py [thinkingR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/tokenizers/deepseek_v4.py [grammarM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/structured_output/__init__.py [grammarR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/structured_output/__init__.py [proposerM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/spec_decode/extract_hidden_states.py [proposerR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/spec_decode/extract_hidden_states.py [configM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/config/vllm.py [configR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/config/vllm.py [cacheM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_cache_interface.py [blockM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/gpu/block_table.py [blockR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/gpu/block_table.py [mambasrcM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/mamba_utils.py [mambasrcR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/mamba_utils.py [sfatest]: https://github.com/vllm-project/vllm-ascend/blob/b8b230112d9d1edb13b8df2cd4d422074c17d640/tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py [ascglm]: https://github.com/vllm-project/vllm-ascend/pull/15913/files [ascmoon]: https://github.com/vllm-project/vllm-ascend/pull/14068/files [ascpcp]: https://github.com/vllm-project/vllm-ascend/pull/15969/files [ascextract]: https://github.com/vllm-project/vllm-ascend/pull/14699/files [range]: vllm-project/vllm@b2f6858...a97dacb [producer]: https://github.com/vllm-project/vllm/pull/53896/files#diff-80ee7e2a62f9dcfbb8a312dc4e3948557e97ef187290daebbcae1e28596bda29 [schedoutM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/output.py#L282-L292 [schedoutR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/output.py#L252-L265 [schedM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/scheduler.py#L1354-L1450 [schedR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/scheduler.py#L1233-L1290 [ascwindow]: https://github.com/vllm-project/vllm-ascend/pull/16120/files - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: shenzhao <shenzhao9@huawei.com> Co-authored-by: shenzhao <shenzhao9@huawei.com>

### What this PR does / why we need it? Add `MooncakeConnectorV2`. More information and RFC will be added later. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? By CI. - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com> Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com> Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com>

### What this PR does / why we need it? #### Summary Upgrade the verified vLLM main revision while retaining v0.28.0 compatibility. | Input | Exact revision | |---|---| | Previous vLLM main | `b2f685834a6456197e7033966fdef52a23f1abcd` | | Target vLLM main | `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` (September 9 target; unchanged by this revision) | | Retained release | `v0.28.0` / `2cf0a6915ce544dc493a0990f2ea38d81601128a` | | Current Ascend PR base | `1b1709b9227ad3e0db2d82b9231c4962919b86f5` | | Reviewed PR head | `225f7cfdbf1c479798643a7d70a7e2031e5466f2` | Current PR-wide diff: **61 files, +819/-418**. The numbered inventory below matches the current GitHub changed-file list one-to-one. Removed changes and historical commit-by-commit progress are not part of this inventory. #### Scope and version handling - Adapt the exact upstream contracts linked below. Where main and release differ, select the lane with `vllm_version_is("0.28.0")`; share logic where both contracts match. - The owner also included baseline dual-version compatibility gaps. In particular, #51031's KV/kernel block-size split predates this main upgrade. Newly merged Ascend consumers from [vllm-project#14068][ascmoon], [vllm-project#14699][ascextract] and [vllm-project#15969][ascpcp] require compatibility handling; they are not mislabeled as newly introduced vLLM breaks. - **No workflow changes remain in this PR.** CPU UT uses the inherited single-main configuration. The existing `main2main` label continues to select main/tag NPU validation. - Keep existing tests and necessary test adaptations; do not add guard-test files or cases. On release only, skip the three unsupported MRV2 extract-hidden-states cases at the owner's request, rather than asserting an initialization error. V1 on both versions and MRV2 on main remain enabled. - The existing owner-authorized release SFA PCP precision exclusion remains a temporary exception, not a precision fix or passing result. The rebased Ascend main now inherits [vllm-project#16306](vllm-project#16306), which temporarily skips DSpark PCP. This PR does not modify that test file or add the skip. A green CI with this inherited skip is not an actual DSpark pass; the independent precision investigation/fix remains outside this PR. - No new patch file is added. This does not add DBO, CUDA Triton attention, NPU ReplaySSM or release MRV2 extract-hidden-states support. #### File-by-file changes and upstream evidence Lane key: **M** = main, **R** = release, **B** = both (possibly version-selected); **T** = test adaptation; **E** = explicitly authorized exception. Upstream links for baseline compatibility or test exclusions document the relevant contract, not a claim that this upgrade introduced the issue. ##### Dependency pin (1 file) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 1. `.github/vllm-main-verified.commit` | M | Advance the verified main pin from b2f6858 to a97dacb; the release tag is unchanged. | [exact upgrade range][range] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Device test adaptations (4 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 2. `tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_compute_slot_mapping.py` | B/T | Keep the inherited windowed-kernel test inputs. Main passes separate KV/kernel sizes and enablement to its reference kernel. Release lacks that reference ABI: first derive CP-local positions, then invoke the release CP=1 physical-slot reference and mask non-local tokens. Adapt the existing out-buffer fixture; add no cases. | [#53896 ABI][uniform]; [main source][blockM]; [release source][blockR]; [Ascend vllm-project#16120][ascwindow] | 10 actual-source CPU simulations passed, including both lanes; selected NPU CI passed; coverage limits in the testing section | | 3. `tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py` | R/E | Temporarily skip only test_dsv3_2_sfa_pcp_model_runner_v2_graph_accuracy on v0.28.0 at the owner's request. Keep main and other cases unchanged; this is NOT a precision fix or an upstream-break claim. | [baseline test being isolated][sfatest] | Owner-authorized precision exception; unresolved | | 4. `tests/e2e/pull_request/one_card/spec_decode/test_extract_hidden_states.py` | R/T | Skip only the three existing cases with use_v2_model_runner=True on v0.28.0, whose upstream configuration rejects extract_hidden_states with MRV2. Keep all V1 cases and main MRV2 execution unchanged; no rejection-contract guard is added. | [#49811 implementation][extract]; [release rejection][configR]; [Ascend vllm-project#14699 cases][ascextract] | Four source-isolated version/runner combinations and Ruff passed; selected device CI passed; coverage limits in the testing section | | 5. `tests/e2e/pull_request/one_card/test_gumbel_sampling.py` | B/T | Adapt the existing Gumbel tests to each lane's signature and installed implementation identity. | [#54282 Gumbel signature][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Existing CPU test adaptations (24 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 6. `tests/ut/core/test_dyntra_lb_scheduler.py` | B/T | Build the actual SchedulerOutput fields for each lane; verify boundary offers only on main while retaining connector/EC metadata checks. This is fixture compatibility, not new Dyntra behavior. | [#51358 scheduler output][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 7. `tests/ut/core/test_recompute_scheduler.py` | B/T | Adapt the existing scheduler test's drain fixture and assertion to main boundary offers versus release partial-tail offers. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 8. `tests/ut/core/test_scheduler_connector_block_state.py` | B/T | Verify Recompute/Dyntra handoff using real lane-specific output fields and cleared scheduler-local state, not only dispatch mocks. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 9. `tests/ut/distributed/ascend_store/test_pool_worker.py` | B/T | Use torch.float32 in the Mamba spec fixture; uniformity/page-size evaluation reaches get_dtype_size and cannot consume the old NumPy dtype. | [#53896][uniform]; [spec definition][cacheM] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 10. `tests/ut/kv_offload/mooncake_v2/helpers.py` | B/T | Add a real KVCacheTensor fixture builder: release shared_by/block-stride/offset fields versus main layers/layer-stride fields. | [#51718 descriptor][layout]; [Ascend vllm-project#14068 consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 11. `tests/ut/kv_offload/mooncake_v2/test_base_worker.py` | B/T | Use the real descriptor helper while retaining ordering, packed-view, SFA virtual-block and invalid-input assertions. | [#51718][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 12. `tests/ut/kv_offload/mooncake_v2/test_utils.py` | B/T | Replace main-shaped descriptor stand-ins with real lane descriptors; preserve storage deduplication, independence and alignment checks. | [#51718][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 13. `tests/ut/kv_offload/test_native_cpu_offload.py` | B/T | Supply data_parallel_size and data_parallel_rank_local in both fixtures: both pinned versions read them. Correct a false release assumption without changing offload behavior. | [main config][offloadM]; [release config][offloadR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 14. `tests/ut/models/test_deepseek_v4_vision_preprocess.py` | B/T | Give _StubInfo and its context a working shared tokenizer so the new processing-info path is tested without an incomplete mock. | [#54886 processor contract][vision] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 15. `tests/ut/models/test_glm5next_kv_cache.py` | B/T | Assert 16 physical storage rows through get_storage_block_size rather than main's nullable raw field; retain the new GLM architecture and its tests. | [#53906][storage]; [Ascend vllm-project#15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 16. `tests/ut/ops/test_routed_experts.py` | B/T | Initialize quant_method.moe_kernel in both fixtures because expert_map already reads it on release too; no production MoE change. | [main expert_map][expertsM]; [release expert_map][expertsR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 17. `tests/ut/patch/platform/test_deepseek_v4_thinking.py` | B/T | Assert the actual reasoning-mode mapping on both pinned tokenizers; remove false release-only expectations while retaining all eight cases. | [main tokenizer][thinkingM]; [release tokenizer][thinkingR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 18. `tests/ut/patch/platform/test_patch_mamba_block_aligned_split.py` | B/T | Supply the common use_eagle_block_drop fixture field and main-only mamba_fine_grained_prefix_cache=False, preserving current indexer configuration. | [#53388 scheduler][schedfixture]; [#53945][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 19. `tests/ut/patch/platform/test_patch_structured_output.py` | B/T | Provide actual request/stop-token fields and validation exceptions on both lanes; retain the {2} stop-token payload and backend-locking assertions. | [main grammar creation][grammarM]; [release grammar creation][grammarR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 20. `tests/ut/patch/platform/test_patch_use_v2_model_runner.py` | B/T | Adapt the existing V1 helper test to the installed lane. | [main configuration][configM]; [release configuration][configR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 21. `tests/ut/patch/platform/test_prefix_cache_cp_patches.py` | B/T | Use the version-aware max-layers helper in the existing shared-tuple planner assertion. | [#53614][eagle]; [#53906][storage]; [#53896][packed] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 22. `tests/ut/patch/worker/test_patch_mamba_utils_uniform_groups.py` | B/T | Verify release's Ascend uniform-group override and main's upstream spec-keyed dictionary/MambaCopyBuffers contract. | [#53896][mamba]; [both-lane source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 23. `tests/ut/spec_decode/test_extract_hidden_states_proposer.py` | B/T | Create CPU buffers without pinned memory on both lanes instead of patching a PIN_MEMORY symbol absent from release; retain proposer behavior assertions. | [main proposer][proposerM]; [release proposer][proposerR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 24. `tests/ut/test_compressed_prefix_cache.py` | B/T | Use physical storage rows and pass replay_boundary to the three real manager calls only on main; retain all cache/hash assertions. | [#53906][storage]; [#53945 cache_blocks][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 25. `tests/ut/worker/test_attn_utils_v2.py` | B/T | Adapt existing storage/binding fixtures and the expected hidden-state cache layout to each lane. | [#53906][storage]; [#52506][bind]; [#51718 hidden-state path][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 26. `tests/ut/worker/test_extract_hidden_states_speculator_v2.py` | B/T | Run main's extract-hidden-states speculator tests only where that module exists; explicitly assert release dispatch raises NotImplementedError before import. | [#49811][extract]; [Ascend vllm-project#14699][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 27. `tests/ut/worker/test_model_runner_v1.py` | B/T | Mock the version-aware Ascend Mamba copy-function producer in the real V1 runner fixture. | [#53896][mamba] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 28. `tests/ut/worker/test_model_runner_v2.py` | B/T | Adapt existing profiling/dummy-call kwargs and PCP buffer access to each lane. Preserve original test inputs. | [#54436][input]; [#52506][dummy]; [#53515][pcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 29. `tests/ut/worker/test_pcp_manager_v2.py` | B/T | Construct main ExecuteModelState with cudagraph_stats and other required current fields; omit fields absent from release. | [#52358 ExecuteModelState][stats] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Runtime adaptations (32 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 30. `vllm_ascend/_310p/worker/v2/block_table.py` | B | Accept and validate optional per-group slot enablement; write PAD for disabled groups in the 310P-owned buffers on both lanes. | [#53896 BlockTables][uniform] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 31. `vllm_ascend/_310p/worker/v2/model_runner.py` | B | Retain release InputBatch max_seq_len_np; forward the shared dummy-state flag; gate main-only circular specs and derive physical storage rows. | [#54436][input]; [#52506][dummy]; [#53896][uniform]; [#53906][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 32. `vllm_ascend/_310p/worker/v2/model_state.py` | B | Forward ubatch_id through the Ascend parent MRO; preserve the existing no-DBO limitation. | [#50945][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 33. `vllm_ascend/attention/context_parallel/common_cp.py` | B | Explicitly declare supports_dcp=True only on the mixin whose implementations already perform DCP, because upstream now defaults to False. | [#55780 capability default][dcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 34. `vllm_ascend/attention/context_parallel/dsa_cp.py` | B | Use get_storage_block_size for DSA CP physical cache geometry instead of directly reading the version-dependent spec field. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 35. `vllm_ascend/attention/dsa_v1.py` | B | Use the same physical-row helper in DSA attention cache geometry; preserve existing attention behavior. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 36. `vllm_ascend/core/kv_cache_interface.py` | B | Keep release's derived storage property without overriding main's optional dataclass field; centralize physical-row derivation, including UniformTypeKVCacheSpecs. | [#53906][storage]; [#51718 spec fields][layout] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 37. `vllm_ascend/core/recompute_scheduler.py` | B | Explicitly separate release producer partial-tail handoff from main boundary snapshots and scheduler-local connector state. Pass CoW copy tasks and EC manager metadata on both lanes: both pins define these fields. Keep CoW lifetime and scheduling policy unchanged. | [#51358 handoff][boundary]; [main producer][schedM]; [release producer][schedR]; [main fields][schedoutM]; [release fields][schedoutR] | Source reviewed; 8 isolated output cases and local formatting passed; selected current-head CI passed; coverage limits in the testing section | | 38. `vllm_ascend/distributed/device_communicators/npu_communicator.py` | B | Initialize fi_pcie_ipc_ar_comm=None because new upstream cleanup/communication code reads it; NPU does not create the CUDA communicator. | [#53576 reader][ipc] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 39. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/base_worker.py` | B | Use the existing version-aware get_kv_cache_tensor_layers helper instead of main-only .layers when registering Mooncake cache views. | [#51718 descriptor][layout]; [Ascend vllm-project#14068 new consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 40. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/utils.py` | B | Use that same layer helper when collecting/deduplicating physical cache storage; preserve packed-layout semantics. | [#51718 descriptor][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 41. `vllm_ascend/models/deepseek_v4/model.py` | B | Advertise the already implemented auxiliary-state-over-PP capability and expose Ascend's existing pp_transport_aux_hidden_states_ prefix to the upstream relay; release safely retains the declarations. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 42. `vllm_ascend/models/minimax_m3/minimax_m3.py` | B | Align existing auxiliary hidden-state PP capability and transport prefix with the new upstream interface, without adding a new model feature. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 43. `vllm_ascend/ops/kimi_mla.py` | M | Relocate the existing concrete Kimi MLA replacement into a lightweight ops module; preserve Ascend-first double inheritance for OOT initialization and forward. No model-module registration side effect. | [#52494 concrete caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated dispatch/MRO checks and Ruff passed; selected current-head CI passed; coverage limits in the testing section | | 44. `vllm_ascend/ops/rel_pos_attention.py` | B | Delete the constructor that only forwarded super incorrectly; inherit each lane's exact upstream signature/initialization, including use_triton_attention. NPU forward is unchanged. | [#55629 constructor/caller][relpos] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 45. `vllm_ascend/ops/triton/v2/block_table/compute_slot_mappings.py` | M | Add only the version-selected disabled-group PAD path. The inherited base now already implements separate KV/kernel addressing with a bounded window; preserve that algorithm, rather than restoring the old full-row staging/direct-load paths. | [#53896 enablement][uniform]; [Ascend vllm-project#16120 inherited mapping][ascwindow] | Source diff verified: only enablement arguments and disabled-group path differ from base; CPU simulations passed; selected NPU CI passed; coverage limits in the testing section | | 46. `vllm_ascend/patch/platform/patch_kv_cache_coordinator.py` | M | Forward drop_eagle_checkpoint_block through the CP coordinator only on main; retain release's older call contract. | [#53614 coordinator][eagle] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 47. `vllm_ascend/patch/platform/patch_kv_cache_utils.py` | B | Bind main's live _get_packed_kv_cache_groups and matching max-layers helper; retain release's old grouping hooks and base GLM/Kimi grouping fixes. | [#53896 planner hooks][packed]; [Ascend vllm-project#15913 architecture][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 48. `vllm_ascend/patch/platform/patch_use_v2_model_runner.py` | B | On release, override only the GPU-specific non-MLA PCP restriction already supported by Ascend; keep all other config rejections. Select the V1-helper patch by version. This is baseline compatibility, not a newly introduced upstream break. | [main config][configM]; [release config][configR]; [Ascend PCP consumer][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 49. `vllm_ascend/patch/worker/patch_bind_kv_cache.py` | B | Accept kv_cache_groups, retain stable layer binding and call share_replayssm_ring_trackers only on main after binding. Do not claim new NPU ReplaySSM support. | [#52506 binding/ring metadata][bind] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 50. `vllm_ascend/patch/worker/patch_mamba_utils.py` | B | Keep release tuple grouping/copy functions and uniform-group override; on main preserve upstream spec-keyed groups and select copy functions by mamba_type in each consumer. | [#53896 grouping][mamba]; [main source][mambasrcM]; [release source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 51. `vllm_ascend/patch/worker/patch_v2/patch_dspark.py` | B | Gate old module-level get_pp_group/_should_share bindings versus main's local imports. Remove obsolete temporary EP-config mutation now that upstream preserves target settings; retain quantization inheritance, PP guard restoration and the original target weight-attribute guard. | [#50514 bindings][dspp]; [#55472 config preservation][dspark] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 52. `vllm_ascend/utils.py` | M | Add the concrete Kimi wrapper mapping to the existing central custom-op registration under an explicit main-only version gate; retain the shared one-time guard and generic release mapping. | [#52494 caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated main/release import, mapping and repeat-call checks passed; selected current-head CI passed; coverage limits in the testing section | | 53. `vllm_ascend/worker/model_runner_v1.py` | B | Produce the lane-correct Mamba copy-function container and use physical storage rows in cache views, preserving the rebased per-layer attention-backend dispatch. | [#53896 V1 producer][producer]; [copy consumer][mamba]; [#53906][storage]; [Ascend vllm-project#15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 54. `vllm_ascend/worker/v2/attn_utils.py` | B | Allocate hidden-state views in release [B,N,H,C] versus main [B,H,N,C] order after removal of the old shape hook; honor padded page size. | [#51718 hidden-state layout][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 55. `vllm_ascend/worker/v2/block_table.py` | B | Version-gate the parent enablement argument and normalize release KV/kernel size tensors at startup and wake-up. Preserve the inherited window sizing and launch configuration, forwarding enablement only on main. | [#53896][uniform]; [#51031][slot]; [main fields][blockM]; [release fields][blockR]; [Ascend vllm-project#16120][ascwindow] | Both-lane actual-source output/padding simulations and Ruff passed; selected NPU CI passed; coverage limits in the testing section | | 56. `vllm_ascend/worker/v2/model_runner.py` | B | Install the existing combined-broadcast patch only on release; main inherits upstream separate PP draft receive/update/broadcast. Retain release InputBatch arguments and dummy-state/PCP buffer adaptations required by the new Ascend override. | [#50514][pp]; [#54436][input]; [#52506][dummy]; [Ascend vllm-project#15969 new override][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 57. `vllm_ascend/worker/v2/model_states/default.py` | B | Accept upstream's optional ubatch_id in prepare_attn, defaulting to zero; keep explicit rejection of unsupported DBO/nonzero microbatches. | [#50945 default model state][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 58. `vllm_ascend/worker/v2/model_states/mamba_hybrid.py` | B | Apply the same prepare_attn signature contract to Mamba hybrid state, preserving the no-DBO guard. | [#50945 Mamba state][ubatchm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 59. `vllm_ascend/worker/v2/pcp_manager.py` | B | Use the already-owned _input_buffers with an explicit non-None assertion instead of a main-only convenience property; this adapts the PCP consumer newly added to the Ascend base. | [#53515 buffer ownership][pcp]; [Ascend vllm-project#15969][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 60. `vllm_ascend/worker/v2/sample/gumbel.py` | B | Select exact public signatures: release's positional logits_cache versus main's required is_drafting before logits_cache. Forward into a shared internal implementation while preserving existing salt, stride, temperature and cache behavior. | [#54282 positional ABI][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 61. `vllm_ascend/worker/v2/spec_decode/__init__.py` | B | Reject release extract-hidden-states MRV2 dispatch explicitly before importing the main-only module; keep main's supported implementation. Do not backport the feature or merely hide collection errors. | [#49811 speculator][extract]; [Ascend vllm-project#14699 new dispatch][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | #### Interface review and limitations The completed b2f6858-to-a97dacb interface report used Ascend baseline `9dfdd529e9bec72d452ecac22d4c512332323a5f`. Its findings were source-reviewed. It is reused at the owner's request; no expensive analyzer rerun is performed for this revision. That report does not automatically cover later rebased Ascend consumers. Those adaptations are linked individually above. The selected current-head integration suite passed; this does not establish exhaustive regression freedom. The release SFA exclusion and inherited upstream DSpark skip remain disclosed limitations; successful required checks will not establish DSpark precision recovery. ### Does this PR introduce _any_ user-facing change? Advance the verified main dependency while preserving supported v0.28.0 behavior through explicit version handling. The release-only unsupported-feature skip changes test reporting to SKIPPED; it does not backport MRV2 extract-hidden-states support or change model execution. ### How was this patch tested? - **Versions:** vLLM main `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` and release `v0.28.0`. NPU CI covers both lanes; CPU UT uses main only. - **CI:** [E2E run 34592721264](https://github.com/vllm-project/vllm-ascend/actions/runs/34592721264) passed on attempt 2 for PR head `225f7cfdb`. This is a rerun success, not a precision-fix claim. - **Coverage limits:** the inherited DSpark PCP skip (vllm-project#16306), owner-authorized release SFA PCP exclusion, and three unsupported release MRV2 extract-hidden-states skips remain. Passing CI does not validate these excluded cases or all PP topologies. - **Local checks:** Ruff lint/format and `git diff --check` passed. Earlier source-isolated CPU checks are noted in the file table; no local NPU or full installed-vLLM validation is claimed. Full `bash format.sh ci` was unavailable on Windows. [slot]: https://github.com/vllm-project/vllm/pull/51031/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [uniform]: https://github.com/vllm-project/vllm/pull/53896/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [mamba]: https://github.com/vllm-project/vllm/pull/53896/files#diff-8ab86225fa08e9a6700851191abcb3f4f8b0bba40e97a82aad700d7a23a4d7ec [packed]: https://github.com/vllm-project/vllm/pull/53896/files#diff-fb2b41380ca86adbba904aff40b18a0815beb73c1198818912e71723383ab604 [storage]: https://github.com/vllm-project/vllm/pull/53906/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [layout]: https://github.com/vllm-project/vllm/pull/51718/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [hidden]: https://github.com/vllm-project/vllm/pull/51718/files#diff-57af80f3ae4b519ad1ac9d1338716420aed243a8f13d652a122ea4661e93708b [boundary]: https://github.com/vllm-project/vllm/pull/51358/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [ipc]: https://github.com/vllm-project/vllm/pull/53576/files#diff-cf486d32b11454e89103000ac0f9a93ee1ccbb8983c02e794b734a65301cd98b [vision]: https://github.com/vllm-project/vllm/pull/54886/files#diff-740d0a4b454d681455df7c9f56361deaafa7a5baaa9dce45e7fa0aefec3e8cbd [kimi]: https://github.com/vllm-project/vllm/pull/52494/files#diff-49368b83ccd7bf5f68204323e211a87440e53b608f5ecf91ff25d4832535b1b9 [kimiwrap]: https://github.com/vllm-project/vllm/pull/52494/files#diff-aad295e6de3607a46cea22f9f1cca768d4937dc5e1d3ca58105513358ed4e4c1 [dcp]: https://github.com/vllm-project/vllm/pull/55780/files#diff-bdb2df4662d59d54517931b86406644ee1e0c33cb3e00afac078d2a9aa550200 [relpos]: https://github.com/vllm-project/vllm/pull/55629/files#diff-53dffba908ca88d6f312c7e27606f8f6fa11fb476e279efa11d712576809e1dd [eagle]: https://github.com/vllm-project/vllm/pull/53614/files#diff-43875c71daa893ef7567e21633d9988c2baf95bef61e3a334a6d584d6444d725 [replay]: https://github.com/vllm-project/vllm/pull/53945/files#diff-97c184a680b7a4bd7d58b11aa0073706533cc887d990eddb98469e7374025ab3 [bind]: https://github.com/vllm-project/vllm/pull/52506/files#diff-645d58630d5acf3a0b07226bfef1e890a584c32502ab97c3d4642070f39a783c [dummy]: https://github.com/vllm-project/vllm/pull/52506/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [pp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-8330021c29feb32718335218ea994b6a770dd182a94b1baeacb7f7f42214afb7 [aux]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2ae789d702f81147ec584f3c0077aa3dedb6ebd424320dc607a44b86e3780874 [dspark]: https://github.com/vllm-project/vllm/pull/55472/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [dspp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [ubatch]: https://github.com/vllm-project/vllm/pull/50945/files#diff-aa6dbff87b81bae23ded2803a01a8c4913fceb6fe39c6d9423a20ad4b89859be [ubatchm]: https://github.com/vllm-project/vllm/pull/50945/files#diff-d6ed06f4278c0f7cd58e0eae8a019b484fba760424e9604284b3529843ba2384 [input]: https://github.com/vllm-project/vllm/pull/54436/files#diff-106f39c08266f186830bb8fcd7fb1df35c0aaa5fd0ac5c17aac64aeddee48902 [pcp]: https://github.com/vllm-project/vllm/pull/53515/files#diff-45dad5fe975c2ec8d02124fa65579cf11bfe9169a94217ceae1de0ea29518127 [gumbel]: https://github.com/vllm-project/vllm/pull/54282/files#diff-02f7c5a06a2d23d544a07d57af16c7ffb74886469c8844385f51a719e329e6b8 [extract]: https://github.com/vllm-project/vllm/pull/49811/files#diff-b13061cd1be0bc80aaa9fce208fe9128aaaad25b3832c5f1693da1d4e8263f5e [schedfixture]: https://github.com/vllm-project/vllm/pull/53388/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [stats]: https://github.com/vllm-project/vllm/pull/52358/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [offloadM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_offload/config.py [offloadR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/kv_offload/config.py [expertsM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/model_executor/layers/fused_moe/routed_experts.py [expertsR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/model_executor/layers/fused_moe/routed_experts.py [thinkingM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/tokenizers/deepseek_v4.py [thinkingR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/tokenizers/deepseek_v4.py [grammarM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/structured_output/__init__.py [grammarR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/structured_output/__init__.py [proposerM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/spec_decode/extract_hidden_states.py [proposerR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/spec_decode/extract_hidden_states.py [configM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/config/vllm.py [configR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/config/vllm.py [cacheM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_cache_interface.py [blockM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/gpu/block_table.py [blockR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/gpu/block_table.py [mambasrcM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/mamba_utils.py [mambasrcR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/mamba_utils.py [sfatest]: https://github.com/vllm-project/vllm-ascend/blob/b8b230112d9d1edb13b8df2cd4d422074c17d640/tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py [ascglm]: https://github.com/vllm-project/vllm-ascend/pull/15913/files [ascmoon]: https://github.com/vllm-project/vllm-ascend/pull/14068/files [ascpcp]: https://github.com/vllm-project/vllm-ascend/pull/15969/files [ascextract]: https://github.com/vllm-project/vllm-ascend/pull/14699/files [range]: vllm-project/vllm@b2f6858...a97dacb [producer]: https://github.com/vllm-project/vllm/pull/53896/files#diff-80ee7e2a62f9dcfbb8a312dc4e3948557e97ef187290daebbcae1e28596bda29 [schedoutM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/output.py#L282-L292 [schedoutR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/output.py#L252-L265 [schedM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/scheduler.py#L1354-L1450 [schedR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/scheduler.py#L1233-L1290 [ascwindow]: https://github.com/vllm-project/vllm-ascend/pull/16120/files - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: shenzhao <shenzhao9@huawei.com> Co-authored-by: shenzhao <shenzhao9@huawei.com>

### What this PR does / why we need it? Add `MooncakeConnectorV2`. More information and RFC will be added later. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? By CI. - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com> Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com> Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com> Signed-off-by: tianming2009 <13246728590@163.com>

### What this PR does / why we need it? #### Summary Upgrade the verified vLLM main revision while retaining v0.28.0 compatibility. | Input | Exact revision | |---|---| | Previous vLLM main | `b2f685834a6456197e7033966fdef52a23f1abcd` | | Target vLLM main | `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` (September 9 target; unchanged by this revision) | | Retained release | `v0.28.0` / `2cf0a6915ce544dc493a0990f2ea38d81601128a` | | Current Ascend PR base | `1b1709b9227ad3e0db2d82b9231c4962919b86f5` | | Reviewed PR head | `225f7cfdbf1c479798643a7d70a7e2031e5466f2` | Current PR-wide diff: **61 files, +819/-418**. The numbered inventory below matches the current GitHub changed-file list one-to-one. Removed changes and historical commit-by-commit progress are not part of this inventory. #### Scope and version handling - Adapt the exact upstream contracts linked below. Where main and release differ, select the lane with `vllm_version_is("0.28.0")`; share logic where both contracts match. - The owner also included baseline dual-version compatibility gaps. In particular, #51031's KV/kernel block-size split predates this main upgrade. Newly merged Ascend consumers from [vllm-project#14068][ascmoon], [vllm-project#14699][ascextract] and [vllm-project#15969][ascpcp] require compatibility handling; they are not mislabeled as newly introduced vLLM breaks. - **No workflow changes remain in this PR.** CPU UT uses the inherited single-main configuration. The existing `main2main` label continues to select main/tag NPU validation. - Keep existing tests and necessary test adaptations; do not add guard-test files or cases. On release only, skip the three unsupported MRV2 extract-hidden-states cases at the owner's request, rather than asserting an initialization error. V1 on both versions and MRV2 on main remain enabled. - The existing owner-authorized release SFA PCP precision exclusion remains a temporary exception, not a precision fix or passing result. The rebased Ascend main now inherits [vllm-project#16306](vllm-project#16306), which temporarily skips DSpark PCP. This PR does not modify that test file or add the skip. A green CI with this inherited skip is not an actual DSpark pass; the independent precision investigation/fix remains outside this PR. - No new patch file is added. This does not add DBO, CUDA Triton attention, NPU ReplaySSM or release MRV2 extract-hidden-states support. #### File-by-file changes and upstream evidence Lane key: **M** = main, **R** = release, **B** = both (possibly version-selected); **T** = test adaptation; **E** = explicitly authorized exception. Upstream links for baseline compatibility or test exclusions document the relevant contract, not a claim that this upgrade introduced the issue. ##### Dependency pin (1 file) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 1. `.github/vllm-main-verified.commit` | M | Advance the verified main pin from b2f6858 to a97dacb; the release tag is unchanged. | [exact upgrade range][range] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Device test adaptations (4 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 2. `tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_compute_slot_mapping.py` | B/T | Keep the inherited windowed-kernel test inputs. Main passes separate KV/kernel sizes and enablement to its reference kernel. Release lacks that reference ABI: first derive CP-local positions, then invoke the release CP=1 physical-slot reference and mask non-local tokens. Adapt the existing out-buffer fixture; add no cases. | [#53896 ABI][uniform]; [main source][blockM]; [release source][blockR]; [Ascend vllm-project#16120][ascwindow] | 10 actual-source CPU simulations passed, including both lanes; selected NPU CI passed; coverage limits in the testing section | | 3. `tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py` | R/E | Temporarily skip only test_dsv3_2_sfa_pcp_model_runner_v2_graph_accuracy on v0.28.0 at the owner's request. Keep main and other cases unchanged; this is NOT a precision fix or an upstream-break claim. | [baseline test being isolated][sfatest] | Owner-authorized precision exception; unresolved | | 4. `tests/e2e/pull_request/one_card/spec_decode/test_extract_hidden_states.py` | R/T | Skip only the three existing cases with use_v2_model_runner=True on v0.28.0, whose upstream configuration rejects extract_hidden_states with MRV2. Keep all V1 cases and main MRV2 execution unchanged; no rejection-contract guard is added. | [#49811 implementation][extract]; [release rejection][configR]; [Ascend vllm-project#14699 cases][ascextract] | Four source-isolated version/runner combinations and Ruff passed; selected device CI passed; coverage limits in the testing section | | 5. `tests/e2e/pull_request/one_card/test_gumbel_sampling.py` | B/T | Adapt the existing Gumbel tests to each lane's signature and installed implementation identity. | [#54282 Gumbel signature][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Existing CPU test adaptations (24 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 6. `tests/ut/core/test_dyntra_lb_scheduler.py` | B/T | Build the actual SchedulerOutput fields for each lane; verify boundary offers only on main while retaining connector/EC metadata checks. This is fixture compatibility, not new Dyntra behavior. | [#51358 scheduler output][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 7. `tests/ut/core/test_recompute_scheduler.py` | B/T | Adapt the existing scheduler test's drain fixture and assertion to main boundary offers versus release partial-tail offers. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 8. `tests/ut/core/test_scheduler_connector_block_state.py` | B/T | Verify Recompute/Dyntra handoff using real lane-specific output fields and cleared scheduler-local state, not only dispatch mocks. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 9. `tests/ut/distributed/ascend_store/test_pool_worker.py` | B/T | Use torch.float32 in the Mamba spec fixture; uniformity/page-size evaluation reaches get_dtype_size and cannot consume the old NumPy dtype. | [#53896][uniform]; [spec definition][cacheM] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 10. `tests/ut/kv_offload/mooncake_v2/helpers.py` | B/T | Add a real KVCacheTensor fixture builder: release shared_by/block-stride/offset fields versus main layers/layer-stride fields. | [#51718 descriptor][layout]; [Ascend vllm-project#14068 consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 11. `tests/ut/kv_offload/mooncake_v2/test_base_worker.py` | B/T | Use the real descriptor helper while retaining ordering, packed-view, SFA virtual-block and invalid-input assertions. | [#51718][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 12. `tests/ut/kv_offload/mooncake_v2/test_utils.py` | B/T | Replace main-shaped descriptor stand-ins with real lane descriptors; preserve storage deduplication, independence and alignment checks. | [#51718][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 13. `tests/ut/kv_offload/test_native_cpu_offload.py` | B/T | Supply data_parallel_size and data_parallel_rank_local in both fixtures: both pinned versions read them. Correct a false release assumption without changing offload behavior. | [main config][offloadM]; [release config][offloadR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 14. `tests/ut/models/test_deepseek_v4_vision_preprocess.py` | B/T | Give _StubInfo and its context a working shared tokenizer so the new processing-info path is tested without an incomplete mock. | [#54886 processor contract][vision] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 15. `tests/ut/models/test_glm5next_kv_cache.py` | B/T | Assert 16 physical storage rows through get_storage_block_size rather than main's nullable raw field; retain the new GLM architecture and its tests. | [#53906][storage]; [Ascend vllm-project#15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 16. `tests/ut/ops/test_routed_experts.py` | B/T | Initialize quant_method.moe_kernel in both fixtures because expert_map already reads it on release too; no production MoE change. | [main expert_map][expertsM]; [release expert_map][expertsR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 17. `tests/ut/patch/platform/test_deepseek_v4_thinking.py` | B/T | Assert the actual reasoning-mode mapping on both pinned tokenizers; remove false release-only expectations while retaining all eight cases. | [main tokenizer][thinkingM]; [release tokenizer][thinkingR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 18. `tests/ut/patch/platform/test_patch_mamba_block_aligned_split.py` | B/T | Supply the common use_eagle_block_drop fixture field and main-only mamba_fine_grained_prefix_cache=False, preserving current indexer configuration. | [#53388 scheduler][schedfixture]; [#53945][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 19. `tests/ut/patch/platform/test_patch_structured_output.py` | B/T | Provide actual request/stop-token fields and validation exceptions on both lanes; retain the {2} stop-token payload and backend-locking assertions. | [main grammar creation][grammarM]; [release grammar creation][grammarR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 20. `tests/ut/patch/platform/test_patch_use_v2_model_runner.py` | B/T | Adapt the existing V1 helper test to the installed lane. | [main configuration][configM]; [release configuration][configR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 21. `tests/ut/patch/platform/test_prefix_cache_cp_patches.py` | B/T | Use the version-aware max-layers helper in the existing shared-tuple planner assertion. | [#53614][eagle]; [#53906][storage]; [#53896][packed] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 22. `tests/ut/patch/worker/test_patch_mamba_utils_uniform_groups.py` | B/T | Verify release's Ascend uniform-group override and main's upstream spec-keyed dictionary/MambaCopyBuffers contract. | [#53896][mamba]; [both-lane source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 23. `tests/ut/spec_decode/test_extract_hidden_states_proposer.py` | B/T | Create CPU buffers without pinned memory on both lanes instead of patching a PIN_MEMORY symbol absent from release; retain proposer behavior assertions. | [main proposer][proposerM]; [release proposer][proposerR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 24. `tests/ut/test_compressed_prefix_cache.py` | B/T | Use physical storage rows and pass replay_boundary to the three real manager calls only on main; retain all cache/hash assertions. | [#53906][storage]; [#53945 cache_blocks][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 25. `tests/ut/worker/test_attn_utils_v2.py` | B/T | Adapt existing storage/binding fixtures and the expected hidden-state cache layout to each lane. | [#53906][storage]; [#52506][bind]; [#51718 hidden-state path][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 26. `tests/ut/worker/test_extract_hidden_states_speculator_v2.py` | B/T | Run main's extract-hidden-states speculator tests only where that module exists; explicitly assert release dispatch raises NotImplementedError before import. | [#49811][extract]; [Ascend vllm-project#14699][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 27. `tests/ut/worker/test_model_runner_v1.py` | B/T | Mock the version-aware Ascend Mamba copy-function producer in the real V1 runner fixture. | [#53896][mamba] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 28. `tests/ut/worker/test_model_runner_v2.py` | B/T | Adapt existing profiling/dummy-call kwargs and PCP buffer access to each lane. Preserve original test inputs. | [#54436][input]; [#52506][dummy]; [#53515][pcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 29. `tests/ut/worker/test_pcp_manager_v2.py` | B/T | Construct main ExecuteModelState with cudagraph_stats and other required current fields; omit fields absent from release. | [#52358 ExecuteModelState][stats] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Runtime adaptations (32 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 30. `vllm_ascend/_310p/worker/v2/block_table.py` | B | Accept and validate optional per-group slot enablement; write PAD for disabled groups in the 310P-owned buffers on both lanes. | [#53896 BlockTables][uniform] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 31. `vllm_ascend/_310p/worker/v2/model_runner.py` | B | Retain release InputBatch max_seq_len_np; forward the shared dummy-state flag; gate main-only circular specs and derive physical storage rows. | [#54436][input]; [#52506][dummy]; [#53896][uniform]; [#53906][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 32. `vllm_ascend/_310p/worker/v2/model_state.py` | B | Forward ubatch_id through the Ascend parent MRO; preserve the existing no-DBO limitation. | [#50945][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 33. `vllm_ascend/attention/context_parallel/common_cp.py` | B | Explicitly declare supports_dcp=True only on the mixin whose implementations already perform DCP, because upstream now defaults to False. | [#55780 capability default][dcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 34. `vllm_ascend/attention/context_parallel/dsa_cp.py` | B | Use get_storage_block_size for DSA CP physical cache geometry instead of directly reading the version-dependent spec field. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 35. `vllm_ascend/attention/dsa_v1.py` | B | Use the same physical-row helper in DSA attention cache geometry; preserve existing attention behavior. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 36. `vllm_ascend/core/kv_cache_interface.py` | B | Keep release's derived storage property without overriding main's optional dataclass field; centralize physical-row derivation, including UniformTypeKVCacheSpecs. | [#53906][storage]; [#51718 spec fields][layout] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 37. `vllm_ascend/core/recompute_scheduler.py` | B | Explicitly separate release producer partial-tail handoff from main boundary snapshots and scheduler-local connector state. Pass CoW copy tasks and EC manager metadata on both lanes: both pins define these fields. Keep CoW lifetime and scheduling policy unchanged. | [#51358 handoff][boundary]; [main producer][schedM]; [release producer][schedR]; [main fields][schedoutM]; [release fields][schedoutR] | Source reviewed; 8 isolated output cases and local formatting passed; selected current-head CI passed; coverage limits in the testing section | | 38. `vllm_ascend/distributed/device_communicators/npu_communicator.py` | B | Initialize fi_pcie_ipc_ar_comm=None because new upstream cleanup/communication code reads it; NPU does not create the CUDA communicator. | [#53576 reader][ipc] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 39. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/base_worker.py` | B | Use the existing version-aware get_kv_cache_tensor_layers helper instead of main-only .layers when registering Mooncake cache views. | [#51718 descriptor][layout]; [Ascend vllm-project#14068 new consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 40. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/utils.py` | B | Use that same layer helper when collecting/deduplicating physical cache storage; preserve packed-layout semantics. | [#51718 descriptor][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 41. `vllm_ascend/models/deepseek_v4/model.py` | B | Advertise the already implemented auxiliary-state-over-PP capability and expose Ascend's existing pp_transport_aux_hidden_states_ prefix to the upstream relay; release safely retains the declarations. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 42. `vllm_ascend/models/minimax_m3/minimax_m3.py` | B | Align existing auxiliary hidden-state PP capability and transport prefix with the new upstream interface, without adding a new model feature. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 43. `vllm_ascend/ops/kimi_mla.py` | M | Relocate the existing concrete Kimi MLA replacement into a lightweight ops module; preserve Ascend-first double inheritance for OOT initialization and forward. No model-module registration side effect. | [#52494 concrete caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated dispatch/MRO checks and Ruff passed; selected current-head CI passed; coverage limits in the testing section | | 44. `vllm_ascend/ops/rel_pos_attention.py` | B | Delete the constructor that only forwarded super incorrectly; inherit each lane's exact upstream signature/initialization, including use_triton_attention. NPU forward is unchanged. | [#55629 constructor/caller][relpos] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 45. `vllm_ascend/ops/triton/v2/block_table/compute_slot_mappings.py` | M | Add only the version-selected disabled-group PAD path. The inherited base now already implements separate KV/kernel addressing with a bounded window; preserve that algorithm, rather than restoring the old full-row staging/direct-load paths. | [#53896 enablement][uniform]; [Ascend vllm-project#16120 inherited mapping][ascwindow] | Source diff verified: only enablement arguments and disabled-group path differ from base; CPU simulations passed; selected NPU CI passed; coverage limits in the testing section | | 46. `vllm_ascend/patch/platform/patch_kv_cache_coordinator.py` | M | Forward drop_eagle_checkpoint_block through the CP coordinator only on main; retain release's older call contract. | [#53614 coordinator][eagle] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 47. `vllm_ascend/patch/platform/patch_kv_cache_utils.py` | B | Bind main's live _get_packed_kv_cache_groups and matching max-layers helper; retain release's old grouping hooks and base GLM/Kimi grouping fixes. | [#53896 planner hooks][packed]; [Ascend vllm-project#15913 architecture][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 48. `vllm_ascend/patch/platform/patch_use_v2_model_runner.py` | B | On release, override only the GPU-specific non-MLA PCP restriction already supported by Ascend; keep all other config rejections. Select the V1-helper patch by version. This is baseline compatibility, not a newly introduced upstream break. | [main config][configM]; [release config][configR]; [Ascend PCP consumer][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 49. `vllm_ascend/patch/worker/patch_bind_kv_cache.py` | B | Accept kv_cache_groups, retain stable layer binding and call share_replayssm_ring_trackers only on main after binding. Do not claim new NPU ReplaySSM support. | [#52506 binding/ring metadata][bind] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 50. `vllm_ascend/patch/worker/patch_mamba_utils.py` | B | Keep release tuple grouping/copy functions and uniform-group override; on main preserve upstream spec-keyed groups and select copy functions by mamba_type in each consumer. | [#53896 grouping][mamba]; [main source][mambasrcM]; [release source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 51. `vllm_ascend/patch/worker/patch_v2/patch_dspark.py` | B | Gate old module-level get_pp_group/_should_share bindings versus main's local imports. Remove obsolete temporary EP-config mutation now that upstream preserves target settings; retain quantization inheritance, PP guard restoration and the original target weight-attribute guard. | [#50514 bindings][dspp]; [#55472 config preservation][dspark] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 52. `vllm_ascend/utils.py` | M | Add the concrete Kimi wrapper mapping to the existing central custom-op registration under an explicit main-only version gate; retain the shared one-time guard and generic release mapping. | [#52494 caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated main/release import, mapping and repeat-call checks passed; selected current-head CI passed; coverage limits in the testing section | | 53. `vllm_ascend/worker/model_runner_v1.py` | B | Produce the lane-correct Mamba copy-function container and use physical storage rows in cache views, preserving the rebased per-layer attention-backend dispatch. | [#53896 V1 producer][producer]; [copy consumer][mamba]; [#53906][storage]; [Ascend vllm-project#15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 54. `vllm_ascend/worker/v2/attn_utils.py` | B | Allocate hidden-state views in release [B,N,H,C] versus main [B,H,N,C] order after removal of the old shape hook; honor padded page size. | [#51718 hidden-state layout][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 55. `vllm_ascend/worker/v2/block_table.py` | B | Version-gate the parent enablement argument and normalize release KV/kernel size tensors at startup and wake-up. Preserve the inherited window sizing and launch configuration, forwarding enablement only on main. | [#53896][uniform]; [#51031][slot]; [main fields][blockM]; [release fields][blockR]; [Ascend vllm-project#16120][ascwindow] | Both-lane actual-source output/padding simulations and Ruff passed; selected NPU CI passed; coverage limits in the testing section | | 56. `vllm_ascend/worker/v2/model_runner.py` | B | Install the existing combined-broadcast patch only on release; main inherits upstream separate PP draft receive/update/broadcast. Retain release InputBatch arguments and dummy-state/PCP buffer adaptations required by the new Ascend override. | [#50514][pp]; [#54436][input]; [#52506][dummy]; [Ascend vllm-project#15969 new override][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 57. `vllm_ascend/worker/v2/model_states/default.py` | B | Accept upstream's optional ubatch_id in prepare_attn, defaulting to zero; keep explicit rejection of unsupported DBO/nonzero microbatches. | [#50945 default model state][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 58. `vllm_ascend/worker/v2/model_states/mamba_hybrid.py` | B | Apply the same prepare_attn signature contract to Mamba hybrid state, preserving the no-DBO guard. | [#50945 Mamba state][ubatchm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 59. `vllm_ascend/worker/v2/pcp_manager.py` | B | Use the already-owned _input_buffers with an explicit non-None assertion instead of a main-only convenience property; this adapts the PCP consumer newly added to the Ascend base. | [#53515 buffer ownership][pcp]; [Ascend vllm-project#15969][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 60. `vllm_ascend/worker/v2/sample/gumbel.py` | B | Select exact public signatures: release's positional logits_cache versus main's required is_drafting before logits_cache. Forward into a shared internal implementation while preserving existing salt, stride, temperature and cache behavior. | [#54282 positional ABI][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 61. `vllm_ascend/worker/v2/spec_decode/__init__.py` | B | Reject release extract-hidden-states MRV2 dispatch explicitly before importing the main-only module; keep main's supported implementation. Do not backport the feature or merely hide collection errors. | [#49811 speculator][extract]; [Ascend vllm-project#14699 new dispatch][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | #### Interface review and limitations The completed b2f6858-to-a97dacb interface report used Ascend baseline `9dfdd529e9bec72d452ecac22d4c512332323a5f`. Its findings were source-reviewed. It is reused at the owner's request; no expensive analyzer rerun is performed for this revision. That report does not automatically cover later rebased Ascend consumers. Those adaptations are linked individually above. The selected current-head integration suite passed; this does not establish exhaustive regression freedom. The release SFA exclusion and inherited upstream DSpark skip remain disclosed limitations; successful required checks will not establish DSpark precision recovery. ### Does this PR introduce _any_ user-facing change? Advance the verified main dependency while preserving supported v0.28.0 behavior through explicit version handling. The release-only unsupported-feature skip changes test reporting to SKIPPED; it does not backport MRV2 extract-hidden-states support or change model execution. ### How was this patch tested? - **Versions:** vLLM main `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` and release `v0.28.0`. NPU CI covers both lanes; CPU UT uses main only. - **CI:** [E2E run 34592721264](https://github.com/vllm-project/vllm-ascend/actions/runs/34592721264) passed on attempt 2 for PR head `225f7cfdb`. This is a rerun success, not a precision-fix claim. - **Coverage limits:** the inherited DSpark PCP skip (vllm-project#16306), owner-authorized release SFA PCP exclusion, and three unsupported release MRV2 extract-hidden-states skips remain. Passing CI does not validate these excluded cases or all PP topologies. - **Local checks:** Ruff lint/format and `git diff --check` passed. Earlier source-isolated CPU checks are noted in the file table; no local NPU or full installed-vLLM validation is claimed. Full `bash format.sh ci` was unavailable on Windows. [slot]: https://github.com/vllm-project/vllm/pull/51031/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [uniform]: https://github.com/vllm-project/vllm/pull/53896/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [mamba]: https://github.com/vllm-project/vllm/pull/53896/files#diff-8ab86225fa08e9a6700851191abcb3f4f8b0bba40e97a82aad700d7a23a4d7ec [packed]: https://github.com/vllm-project/vllm/pull/53896/files#diff-fb2b41380ca86adbba904aff40b18a0815beb73c1198818912e71723383ab604 [storage]: https://github.com/vllm-project/vllm/pull/53906/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [layout]: https://github.com/vllm-project/vllm/pull/51718/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [hidden]: https://github.com/vllm-project/vllm/pull/51718/files#diff-57af80f3ae4b519ad1ac9d1338716420aed243a8f13d652a122ea4661e93708b [boundary]: https://github.com/vllm-project/vllm/pull/51358/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [ipc]: https://github.com/vllm-project/vllm/pull/53576/files#diff-cf486d32b11454e89103000ac0f9a93ee1ccbb8983c02e794b734a65301cd98b [vision]: https://github.com/vllm-project/vllm/pull/54886/files#diff-740d0a4b454d681455df7c9f56361deaafa7a5baaa9dce45e7fa0aefec3e8cbd [kimi]: https://github.com/vllm-project/vllm/pull/52494/files#diff-49368b83ccd7bf5f68204323e211a87440e53b608f5ecf91ff25d4832535b1b9 [kimiwrap]: https://github.com/vllm-project/vllm/pull/52494/files#diff-aad295e6de3607a46cea22f9f1cca768d4937dc5e1d3ca58105513358ed4e4c1 [dcp]: https://github.com/vllm-project/vllm/pull/55780/files#diff-bdb2df4662d59d54517931b86406644ee1e0c33cb3e00afac078d2a9aa550200 [relpos]: https://github.com/vllm-project/vllm/pull/55629/files#diff-53dffba908ca88d6f312c7e27606f8f6fa11fb476e279efa11d712576809e1dd [eagle]: https://github.com/vllm-project/vllm/pull/53614/files#diff-43875c71daa893ef7567e21633d9988c2baf95bef61e3a334a6d584d6444d725 [replay]: https://github.com/vllm-project/vllm/pull/53945/files#diff-97c184a680b7a4bd7d58b11aa0073706533cc887d990eddb98469e7374025ab3 [bind]: https://github.com/vllm-project/vllm/pull/52506/files#diff-645d58630d5acf3a0b07226bfef1e890a584c32502ab97c3d4642070f39a783c [dummy]: https://github.com/vllm-project/vllm/pull/52506/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [pp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-8330021c29feb32718335218ea994b6a770dd182a94b1baeacb7f7f42214afb7 [aux]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2ae789d702f81147ec584f3c0077aa3dedb6ebd424320dc607a44b86e3780874 [dspark]: https://github.com/vllm-project/vllm/pull/55472/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [dspp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [ubatch]: https://github.com/vllm-project/vllm/pull/50945/files#diff-aa6dbff87b81bae23ded2803a01a8c4913fceb6fe39c6d9423a20ad4b89859be [ubatchm]: https://github.com/vllm-project/vllm/pull/50945/files#diff-d6ed06f4278c0f7cd58e0eae8a019b484fba760424e9604284b3529843ba2384 [input]: https://github.com/vllm-project/vllm/pull/54436/files#diff-106f39c08266f186830bb8fcd7fb1df35c0aaa5fd0ac5c17aac64aeddee48902 [pcp]: https://github.com/vllm-project/vllm/pull/53515/files#diff-45dad5fe975c2ec8d02124fa65579cf11bfe9169a94217ceae1de0ea29518127 [gumbel]: https://github.com/vllm-project/vllm/pull/54282/files#diff-02f7c5a06a2d23d544a07d57af16c7ffb74886469c8844385f51a719e329e6b8 [extract]: https://github.com/vllm-project/vllm/pull/49811/files#diff-b13061cd1be0bc80aaa9fce208fe9128aaaad25b3832c5f1693da1d4e8263f5e [schedfixture]: https://github.com/vllm-project/vllm/pull/53388/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [stats]: https://github.com/vllm-project/vllm/pull/52358/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [offloadM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_offload/config.py [offloadR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/kv_offload/config.py [expertsM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/model_executor/layers/fused_moe/routed_experts.py [expertsR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/model_executor/layers/fused_moe/routed_experts.py [thinkingM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/tokenizers/deepseek_v4.py [thinkingR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/tokenizers/deepseek_v4.py [grammarM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/structured_output/__init__.py [grammarR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/structured_output/__init__.py [proposerM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/spec_decode/extract_hidden_states.py [proposerR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/spec_decode/extract_hidden_states.py [configM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/config/vllm.py [configR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/config/vllm.py [cacheM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_cache_interface.py [blockM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/gpu/block_table.py [blockR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/gpu/block_table.py [mambasrcM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/mamba_utils.py [mambasrcR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/mamba_utils.py [sfatest]: https://github.com/vllm-project/vllm-ascend/blob/b8b230112d9d1edb13b8df2cd4d422074c17d640/tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py [ascglm]: https://github.com/vllm-project/vllm-ascend/pull/15913/files [ascmoon]: https://github.com/vllm-project/vllm-ascend/pull/14068/files [ascpcp]: https://github.com/vllm-project/vllm-ascend/pull/15969/files [ascextract]: https://github.com/vllm-project/vllm-ascend/pull/14699/files [range]: vllm-project/vllm@b2f6858...a97dacb [producer]: https://github.com/vllm-project/vllm/pull/53896/files#diff-80ee7e2a62f9dcfbb8a312dc4e3948557e97ef187290daebbcae1e28596bda29 [schedoutM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/output.py#L282-L292 [schedoutR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/output.py#L252-L265 [schedM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/scheduler.py#L1354-L1450 [schedR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/scheduler.py#L1233-L1290 [ascwindow]: https://github.com/vllm-project/vllm-ascend/pull/16120/files - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: shenzhao <shenzhao9@huawei.com> Co-authored-by: shenzhao <shenzhao9@huawei.com> Signed-off-by: tianming2009 <13246728590@163.com>

### What this PR does / why we need it? Add `MooncakeConnectorV2`. More information and RFC will be added later. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? By CI. - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com> Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com> Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com> Signed-off-by: like-0517 <ithwlike@126.com>

### What this PR does / why we need it? #### Summary Upgrade the verified vLLM main revision while retaining v0.28.0 compatibility. | Input | Exact revision | |---|---| | Previous vLLM main | `b2f685834a6456197e7033966fdef52a23f1abcd` | | Target vLLM main | `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` (September 9 target; unchanged by this revision) | | Retained release | `v0.28.0` / `2cf0a6915ce544dc493a0990f2ea38d81601128a` | | Current Ascend PR base | `1b1709b9227ad3e0db2d82b9231c4962919b86f5` | | Reviewed PR head | `225f7cfdbf1c479798643a7d70a7e2031e5466f2` | Current PR-wide diff: **61 files, +819/-418**. The numbered inventory below matches the current GitHub changed-file list one-to-one. Removed changes and historical commit-by-commit progress are not part of this inventory. #### Scope and version handling - Adapt the exact upstream contracts linked below. Where main and release differ, select the lane with `vllm_version_is("0.28.0")`; share logic where both contracts match. - The owner also included baseline dual-version compatibility gaps. In particular, #51031's KV/kernel block-size split predates this main upgrade. Newly merged Ascend consumers from [vllm-project#14068][ascmoon], [vllm-project#14699][ascextract] and [vllm-project#15969][ascpcp] require compatibility handling; they are not mislabeled as newly introduced vLLM breaks. - **No workflow changes remain in this PR.** CPU UT uses the inherited single-main configuration. The existing `main2main` label continues to select main/tag NPU validation. - Keep existing tests and necessary test adaptations; do not add guard-test files or cases. On release only, skip the three unsupported MRV2 extract-hidden-states cases at the owner's request, rather than asserting an initialization error. V1 on both versions and MRV2 on main remain enabled. - The existing owner-authorized release SFA PCP precision exclusion remains a temporary exception, not a precision fix or passing result. The rebased Ascend main now inherits [vllm-project#16306](vllm-project#16306), which temporarily skips DSpark PCP. This PR does not modify that test file or add the skip. A green CI with this inherited skip is not an actual DSpark pass; the independent precision investigation/fix remains outside this PR. - No new patch file is added. This does not add DBO, CUDA Triton attention, NPU ReplaySSM or release MRV2 extract-hidden-states support. #### File-by-file changes and upstream evidence Lane key: **M** = main, **R** = release, **B** = both (possibly version-selected); **T** = test adaptation; **E** = explicitly authorized exception. Upstream links for baseline compatibility or test exclusions document the relevant contract, not a claim that this upgrade introduced the issue. ##### Dependency pin (1 file) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 1. `.github/vllm-main-verified.commit` | M | Advance the verified main pin from b2f6858 to a97dacb; the release tag is unchanged. | [exact upgrade range][range] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Device test adaptations (4 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 2. `tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_compute_slot_mapping.py` | B/T | Keep the inherited windowed-kernel test inputs. Main passes separate KV/kernel sizes and enablement to its reference kernel. Release lacks that reference ABI: first derive CP-local positions, then invoke the release CP=1 physical-slot reference and mask non-local tokens. Adapt the existing out-buffer fixture; add no cases. | [#53896 ABI][uniform]; [main source][blockM]; [release source][blockR]; [Ascend vllm-project#16120][ascwindow] | 10 actual-source CPU simulations passed, including both lanes; selected NPU CI passed; coverage limits in the testing section | | 3. `tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py` | R/E | Temporarily skip only test_dsv3_2_sfa_pcp_model_runner_v2_graph_accuracy on v0.28.0 at the owner's request. Keep main and other cases unchanged; this is NOT a precision fix or an upstream-break claim. | [baseline test being isolated][sfatest] | Owner-authorized precision exception; unresolved | | 4. `tests/e2e/pull_request/one_card/spec_decode/test_extract_hidden_states.py` | R/T | Skip only the three existing cases with use_v2_model_runner=True on v0.28.0, whose upstream configuration rejects extract_hidden_states with MRV2. Keep all V1 cases and main MRV2 execution unchanged; no rejection-contract guard is added. | [#49811 implementation][extract]; [release rejection][configR]; [Ascend vllm-project#14699 cases][ascextract] | Four source-isolated version/runner combinations and Ruff passed; selected device CI passed; coverage limits in the testing section | | 5. `tests/e2e/pull_request/one_card/test_gumbel_sampling.py` | B/T | Adapt the existing Gumbel tests to each lane's signature and installed implementation identity. | [#54282 Gumbel signature][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Existing CPU test adaptations (24 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 6. `tests/ut/core/test_dyntra_lb_scheduler.py` | B/T | Build the actual SchedulerOutput fields for each lane; verify boundary offers only on main while retaining connector/EC metadata checks. This is fixture compatibility, not new Dyntra behavior. | [#51358 scheduler output][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 7. `tests/ut/core/test_recompute_scheduler.py` | B/T | Adapt the existing scheduler test's drain fixture and assertion to main boundary offers versus release partial-tail offers. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 8. `tests/ut/core/test_scheduler_connector_block_state.py` | B/T | Verify Recompute/Dyntra handoff using real lane-specific output fields and cleared scheduler-local state, not only dispatch mocks. | [#51358][boundary] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 9. `tests/ut/distributed/ascend_store/test_pool_worker.py` | B/T | Use torch.float32 in the Mamba spec fixture; uniformity/page-size evaluation reaches get_dtype_size and cannot consume the old NumPy dtype. | [#53896][uniform]; [spec definition][cacheM] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 10. `tests/ut/kv_offload/mooncake_v2/helpers.py` | B/T | Add a real KVCacheTensor fixture builder: release shared_by/block-stride/offset fields versus main layers/layer-stride fields. | [#51718 descriptor][layout]; [Ascend vllm-project#14068 consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 11. `tests/ut/kv_offload/mooncake_v2/test_base_worker.py` | B/T | Use the real descriptor helper while retaining ordering, packed-view, SFA virtual-block and invalid-input assertions. | [#51718][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 12. `tests/ut/kv_offload/mooncake_v2/test_utils.py` | B/T | Replace main-shaped descriptor stand-ins with real lane descriptors; preserve storage deduplication, independence and alignment checks. | [#51718][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 13. `tests/ut/kv_offload/test_native_cpu_offload.py` | B/T | Supply data_parallel_size and data_parallel_rank_local in both fixtures: both pinned versions read them. Correct a false release assumption without changing offload behavior. | [main config][offloadM]; [release config][offloadR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 14. `tests/ut/models/test_deepseek_v4_vision_preprocess.py` | B/T | Give _StubInfo and its context a working shared tokenizer so the new processing-info path is tested without an incomplete mock. | [#54886 processor contract][vision] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 15. `tests/ut/models/test_glm5next_kv_cache.py` | B/T | Assert 16 physical storage rows through get_storage_block_size rather than main's nullable raw field; retain the new GLM architecture and its tests. | [#53906][storage]; [Ascend vllm-project#15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 16. `tests/ut/ops/test_routed_experts.py` | B/T | Initialize quant_method.moe_kernel in both fixtures because expert_map already reads it on release too; no production MoE change. | [main expert_map][expertsM]; [release expert_map][expertsR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 17. `tests/ut/patch/platform/test_deepseek_v4_thinking.py` | B/T | Assert the actual reasoning-mode mapping on both pinned tokenizers; remove false release-only expectations while retaining all eight cases. | [main tokenizer][thinkingM]; [release tokenizer][thinkingR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 18. `tests/ut/patch/platform/test_patch_mamba_block_aligned_split.py` | B/T | Supply the common use_eagle_block_drop fixture field and main-only mamba_fine_grained_prefix_cache=False, preserving current indexer configuration. | [#53388 scheduler][schedfixture]; [#53945][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 19. `tests/ut/patch/platform/test_patch_structured_output.py` | B/T | Provide actual request/stop-token fields and validation exceptions on both lanes; retain the {2} stop-token payload and backend-locking assertions. | [main grammar creation][grammarM]; [release grammar creation][grammarR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 20. `tests/ut/patch/platform/test_patch_use_v2_model_runner.py` | B/T | Adapt the existing V1 helper test to the installed lane. | [main configuration][configM]; [release configuration][configR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 21. `tests/ut/patch/platform/test_prefix_cache_cp_patches.py` | B/T | Use the version-aware max-layers helper in the existing shared-tuple planner assertion. | [#53614][eagle]; [#53906][storage]; [#53896][packed] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 22. `tests/ut/patch/worker/test_patch_mamba_utils_uniform_groups.py` | B/T | Verify release's Ascend uniform-group override and main's upstream spec-keyed dictionary/MambaCopyBuffers contract. | [#53896][mamba]; [both-lane source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 23. `tests/ut/spec_decode/test_extract_hidden_states_proposer.py` | B/T | Create CPU buffers without pinned memory on both lanes instead of patching a PIN_MEMORY symbol absent from release; retain proposer behavior assertions. | [main proposer][proposerM]; [release proposer][proposerR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 24. `tests/ut/test_compressed_prefix_cache.py` | B/T | Use physical storage rows and pass replay_boundary to the three real manager calls only on main; retain all cache/hash assertions. | [#53906][storage]; [#53945 cache_blocks][replay] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 25. `tests/ut/worker/test_attn_utils_v2.py` | B/T | Adapt existing storage/binding fixtures and the expected hidden-state cache layout to each lane. | [#53906][storage]; [#52506][bind]; [#51718 hidden-state path][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 26. `tests/ut/worker/test_extract_hidden_states_speculator_v2.py` | B/T | Run main's extract-hidden-states speculator tests only where that module exists; explicitly assert release dispatch raises NotImplementedError before import. | [#49811][extract]; [Ascend vllm-project#14699][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 27. `tests/ut/worker/test_model_runner_v1.py` | B/T | Mock the version-aware Ascend Mamba copy-function producer in the real V1 runner fixture. | [#53896][mamba] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 28. `tests/ut/worker/test_model_runner_v2.py` | B/T | Adapt existing profiling/dummy-call kwargs and PCP buffer access to each lane. Preserve original test inputs. | [#54436][input]; [#52506][dummy]; [#53515][pcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 29. `tests/ut/worker/test_pcp_manager_v2.py` | B/T | Construct main ExecuteModelState with cudagraph_stats and other required current fields; omit fields absent from release. | [#52358 ExecuteModelState][stats] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | ##### Runtime adaptations (32 files) | # / File | Lane | Change and reason | Upstream code / cause | Verification | |---|---|---|---|---| | 30. `vllm_ascend/_310p/worker/v2/block_table.py` | B | Accept and validate optional per-group slot enablement; write PAD for disabled groups in the 310P-owned buffers on both lanes. | [#53896 BlockTables][uniform] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 31. `vllm_ascend/_310p/worker/v2/model_runner.py` | B | Retain release InputBatch max_seq_len_np; forward the shared dummy-state flag; gate main-only circular specs and derive physical storage rows. | [#54436][input]; [#52506][dummy]; [#53896][uniform]; [#53906][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 32. `vllm_ascend/_310p/worker/v2/model_state.py` | B | Forward ubatch_id through the Ascend parent MRO; preserve the existing no-DBO limitation. | [#50945][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 33. `vllm_ascend/attention/context_parallel/common_cp.py` | B | Explicitly declare supports_dcp=True only on the mixin whose implementations already perform DCP, because upstream now defaults to False. | [#55780 capability default][dcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 34. `vllm_ascend/attention/context_parallel/dsa_cp.py` | B | Use get_storage_block_size for DSA CP physical cache geometry instead of directly reading the version-dependent spec field. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 35. `vllm_ascend/attention/dsa_v1.py` | B | Use the same physical-row helper in DSA attention cache geometry; preserve existing attention behavior. | [#53906 storage contract][storage] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 36. `vllm_ascend/core/kv_cache_interface.py` | B | Keep release's derived storage property without overriding main's optional dataclass field; centralize physical-row derivation, including UniformTypeKVCacheSpecs. | [#53906][storage]; [#51718 spec fields][layout] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 37. `vllm_ascend/core/recompute_scheduler.py` | B | Explicitly separate release producer partial-tail handoff from main boundary snapshots and scheduler-local connector state. Pass CoW copy tasks and EC manager metadata on both lanes: both pins define these fields. Keep CoW lifetime and scheduling policy unchanged. | [#51358 handoff][boundary]; [main producer][schedM]; [release producer][schedR]; [main fields][schedoutM]; [release fields][schedoutR] | Source reviewed; 8 isolated output cases and local formatting passed; selected current-head CI passed; coverage limits in the testing section | | 38. `vllm_ascend/distributed/device_communicators/npu_communicator.py` | B | Initialize fi_pcie_ipc_ar_comm=None because new upstream cleanup/communication code reads it; NPU does not create the CUDA communicator. | [#53576 reader][ipc] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 39. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/base_worker.py` | B | Use the existing version-aware get_kv_cache_tensor_layers helper instead of main-only .layers when registering Mooncake cache views. | [#51718 descriptor][layout]; [Ascend vllm-project#14068 new consumer][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 40. `vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake/utils.py` | B | Use that same layer helper when collecting/deduplicating physical cache storage; preserve packed-layout semantics. | [#51718 descriptor][layout]; [Ascend vllm-project#14068][ascmoon] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 41. `vllm_ascend/models/deepseek_v4/model.py` | B | Advertise the already implemented auxiliary-state-over-PP capability and expose Ascend's existing pp_transport_aux_hidden_states_ prefix to the upstream relay; release safely retains the declarations. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 42. `vllm_ascend/models/minimax_m3/minimax_m3.py` | B | Align existing auxiliary hidden-state PP capability and transport prefix with the new upstream interface, without adding a new model feature. | [#50514 model protocol][aux] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 43. `vllm_ascend/ops/kimi_mla.py` | M | Relocate the existing concrete Kimi MLA replacement into a lightweight ops module; preserve Ascend-first double inheritance for OOT initialization and forward. No model-module registration side effect. | [#52494 concrete caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated dispatch/MRO checks and Ruff passed; selected current-head CI passed; coverage limits in the testing section | | 44. `vllm_ascend/ops/rel_pos_attention.py` | B | Delete the constructor that only forwarded super incorrectly; inherit each lane's exact upstream signature/initialization, including use_triton_attention. NPU forward is unchanged. | [#55629 constructor/caller][relpos] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 45. `vllm_ascend/ops/triton/v2/block_table/compute_slot_mappings.py` | M | Add only the version-selected disabled-group PAD path. The inherited base now already implements separate KV/kernel addressing with a bounded window; preserve that algorithm, rather than restoring the old full-row staging/direct-load paths. | [#53896 enablement][uniform]; [Ascend vllm-project#16120 inherited mapping][ascwindow] | Source diff verified: only enablement arguments and disabled-group path differ from base; CPU simulations passed; selected NPU CI passed; coverage limits in the testing section | | 46. `vllm_ascend/patch/platform/patch_kv_cache_coordinator.py` | M | Forward drop_eagle_checkpoint_block through the CP coordinator only on main; retain release's older call contract. | [#53614 coordinator][eagle] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 47. `vllm_ascend/patch/platform/patch_kv_cache_utils.py` | B | Bind main's live _get_packed_kv_cache_groups and matching max-layers helper; retain release's old grouping hooks and base GLM/Kimi grouping fixes. | [#53896 planner hooks][packed]; [Ascend vllm-project#15913 architecture][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 48. `vllm_ascend/patch/platform/patch_use_v2_model_runner.py` | B | On release, override only the GPU-specific non-MLA PCP restriction already supported by Ascend; keep all other config rejections. Select the V1-helper patch by version. This is baseline compatibility, not a newly introduced upstream break. | [main config][configM]; [release config][configR]; [Ascend PCP consumer][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 49. `vllm_ascend/patch/worker/patch_bind_kv_cache.py` | B | Accept kv_cache_groups, retain stable layer binding and call share_replayssm_ring_trackers only on main after binding. Do not claim new NPU ReplaySSM support. | [#52506 binding/ring metadata][bind] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 50. `vllm_ascend/patch/worker/patch_mamba_utils.py` | B | Keep release tuple grouping/copy functions and uniform-group override; on main preserve upstream spec-keyed groups and select copy functions by mamba_type in each consumer. | [#53896 grouping][mamba]; [main source][mambasrcM]; [release source][mambasrcR] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 51. `vllm_ascend/patch/worker/patch_v2/patch_dspark.py` | B | Gate old module-level get_pp_group/_should_share bindings versus main's local imports. Remove obsolete temporary EP-config mutation now that upstream preserves target settings; retain quantization inheritance, PP guard restoration and the original target weight-attribute guard. | [#50514 bindings][dspp]; [#55472 config preservation][dspark] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 52. `vllm_ascend/utils.py` | M | Add the concrete Kimi wrapper mapping to the existing central custom-op registration under an explicit main-only version gate; retain the shared one-time guard and generic release mapping. | [#52494 caller][kimi]; [upstream wrapper][kimiwrap] | Source-isolated main/release import, mapping and repeat-call checks passed; selected current-head CI passed; coverage limits in the testing section | | 53. `vllm_ascend/worker/model_runner_v1.py` | B | Produce the lane-correct Mamba copy-function container and use physical storage rows in cache views, preserving the rebased per-layer attention-backend dispatch. | [#53896 V1 producer][producer]; [copy consumer][mamba]; [#53906][storage]; [Ascend vllm-project#15913][ascglm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 54. `vllm_ascend/worker/v2/attn_utils.py` | B | Allocate hidden-state views in release [B,N,H,C] versus main [B,H,N,C] order after removal of the old shape hook; honor padded page size. | [#51718 hidden-state layout][hidden] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 55. `vllm_ascend/worker/v2/block_table.py` | B | Version-gate the parent enablement argument and normalize release KV/kernel size tensors at startup and wake-up. Preserve the inherited window sizing and launch configuration, forwarding enablement only on main. | [#53896][uniform]; [#51031][slot]; [main fields][blockM]; [release fields][blockR]; [Ascend vllm-project#16120][ascwindow] | Both-lane actual-source output/padding simulations and Ruff passed; selected NPU CI passed; coverage limits in the testing section | | 56. `vllm_ascend/worker/v2/model_runner.py` | B | Install the existing combined-broadcast patch only on release; main inherits upstream separate PP draft receive/update/broadcast. Retain release InputBatch arguments and dummy-state/PCP buffer adaptations required by the new Ascend override. | [#50514][pp]; [#54436][input]; [#52506][dummy]; [Ascend vllm-project#15969 new override][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 57. `vllm_ascend/worker/v2/model_states/default.py` | B | Accept upstream's optional ubatch_id in prepare_attn, defaulting to zero; keep explicit rejection of unsupported DBO/nonzero microbatches. | [#50945 default model state][ubatch] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 58. `vllm_ascend/worker/v2/model_states/mamba_hybrid.py` | B | Apply the same prepare_attn signature contract to Mamba hybrid state, preserving the no-DBO guard. | [#50945 Mamba state][ubatchm] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 59. `vllm_ascend/worker/v2/pcp_manager.py` | B | Use the already-owned _input_buffers with an explicit non-None assertion instead of a main-only convenience property; this adapts the PCP consumer newly added to the Ascend base. | [#53515 buffer ownership][pcp]; [Ascend vllm-project#15969][ascpcp] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 60. `vllm_ascend/worker/v2/sample/gumbel.py` | B | Select exact public signatures: release's positional logits_cache versus main's required is_drafting before logits_cache. Forward into a shared internal implementation while preserving existing salt, stride, temperature and cache behavior. | [#54282 positional ABI][gumbel] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | | 61. `vllm_ascend/worker/v2/spec_decode/__init__.py` | B | Reject release extract-hidden-states MRV2 dispatch explicitly before importing the main-only module; keep main's supported implementation. Do not backport the feature or merely hide collection errors. | [#49811 speculator][extract]; [Ascend vllm-project#14699 new dispatch][ascextract] | Source reviewed; selected current-head CI passed; coverage limits in the testing section | #### Interface review and limitations The completed b2f6858-to-a97dacb interface report used Ascend baseline `9dfdd529e9bec72d452ecac22d4c512332323a5f`. Its findings were source-reviewed. It is reused at the owner's request; no expensive analyzer rerun is performed for this revision. That report does not automatically cover later rebased Ascend consumers. Those adaptations are linked individually above. The selected current-head integration suite passed; this does not establish exhaustive regression freedom. The release SFA exclusion and inherited upstream DSpark skip remain disclosed limitations; successful required checks will not establish DSpark precision recovery. ### Does this PR introduce _any_ user-facing change? Advance the verified main dependency while preserving supported v0.28.0 behavior through explicit version handling. The release-only unsupported-feature skip changes test reporting to SKIPPED; it does not backport MRV2 extract-hidden-states support or change model execution. ### How was this patch tested? - **Versions:** vLLM main `a97dacb7106ee49f39f3d1fc6ae1800ff724e01d` and release `v0.28.0`. NPU CI covers both lanes; CPU UT uses main only. - **CI:** [E2E run 34592721264](https://github.com/vllm-project/vllm-ascend/actions/runs/34592721264) passed on attempt 2 for PR head `225f7cfdb`. This is a rerun success, not a precision-fix claim. - **Coverage limits:** the inherited DSpark PCP skip (vllm-project#16306), owner-authorized release SFA PCP exclusion, and three unsupported release MRV2 extract-hidden-states skips remain. Passing CI does not validate these excluded cases or all PP topologies. - **Local checks:** Ruff lint/format and `git diff --check` passed. Earlier source-isolated CPU checks are noted in the file table; no local NPU or full installed-vLLM validation is claimed. Full `bash format.sh ci` was unavailable on Windows. [slot]: https://github.com/vllm-project/vllm/pull/51031/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [uniform]: https://github.com/vllm-project/vllm/pull/53896/files#diff-21052649468f36e592c9ed378a9cd7b4615c558fb4d10f034f7b4268d3b6f9e1 [mamba]: https://github.com/vllm-project/vllm/pull/53896/files#diff-8ab86225fa08e9a6700851191abcb3f4f8b0bba40e97a82aad700d7a23a4d7ec [packed]: https://github.com/vllm-project/vllm/pull/53896/files#diff-fb2b41380ca86adbba904aff40b18a0815beb73c1198818912e71723383ab604 [storage]: https://github.com/vllm-project/vllm/pull/53906/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [layout]: https://github.com/vllm-project/vllm/pull/51718/files#diff-f76cdfbf02dacd9dffbfbd0d9ad68a7a6ac0d8aed70834f95a2ae8ccd2e333cb [hidden]: https://github.com/vllm-project/vllm/pull/51718/files#diff-57af80f3ae4b519ad1ac9d1338716420aed243a8f13d652a122ea4661e93708b [boundary]: https://github.com/vllm-project/vllm/pull/51358/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [ipc]: https://github.com/vllm-project/vllm/pull/53576/files#diff-cf486d32b11454e89103000ac0f9a93ee1ccbb8983c02e794b734a65301cd98b [vision]: https://github.com/vllm-project/vllm/pull/54886/files#diff-740d0a4b454d681455df7c9f56361deaafa7a5baaa9dce45e7fa0aefec3e8cbd [kimi]: https://github.com/vllm-project/vllm/pull/52494/files#diff-49368b83ccd7bf5f68204323e211a87440e53b608f5ecf91ff25d4832535b1b9 [kimiwrap]: https://github.com/vllm-project/vllm/pull/52494/files#diff-aad295e6de3607a46cea22f9f1cca768d4937dc5e1d3ca58105513358ed4e4c1 [dcp]: https://github.com/vllm-project/vllm/pull/55780/files#diff-bdb2df4662d59d54517931b86406644ee1e0c33cb3e00afac078d2a9aa550200 [relpos]: https://github.com/vllm-project/vllm/pull/55629/files#diff-53dffba908ca88d6f312c7e27606f8f6fa11fb476e279efa11d712576809e1dd [eagle]: https://github.com/vllm-project/vllm/pull/53614/files#diff-43875c71daa893ef7567e21633d9988c2baf95bef61e3a334a6d584d6444d725 [replay]: https://github.com/vllm-project/vllm/pull/53945/files#diff-97c184a680b7a4bd7d58b11aa0073706533cc887d990eddb98469e7374025ab3 [bind]: https://github.com/vllm-project/vllm/pull/52506/files#diff-645d58630d5acf3a0b07226bfef1e890a584c32502ab97c3d4642070f39a783c [dummy]: https://github.com/vllm-project/vllm/pull/52506/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [pp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-8330021c29feb32718335218ea994b6a770dd182a94b1baeacb7f7f42214afb7 [aux]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2ae789d702f81147ec584f3c0077aa3dedb6ebd424320dc607a44b86e3780874 [dspark]: https://github.com/vllm-project/vllm/pull/55472/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [dspp]: https://github.com/vllm-project/vllm/pull/50514/files#diff-2223c5e6b44b302db9bff4023777cc88b4427f4fb9d4a04476f6d6e4bd687393 [ubatch]: https://github.com/vllm-project/vllm/pull/50945/files#diff-aa6dbff87b81bae23ded2803a01a8c4913fceb6fe39c6d9423a20ad4b89859be [ubatchm]: https://github.com/vllm-project/vllm/pull/50945/files#diff-d6ed06f4278c0f7cd58e0eae8a019b484fba760424e9604284b3529843ba2384 [input]: https://github.com/vllm-project/vllm/pull/54436/files#diff-106f39c08266f186830bb8fcd7fb1df35c0aaa5fd0ac5c17aac64aeddee48902 [pcp]: https://github.com/vllm-project/vllm/pull/53515/files#diff-45dad5fe975c2ec8d02124fa65579cf11bfe9169a94217ceae1de0ea29518127 [gumbel]: https://github.com/vllm-project/vllm/pull/54282/files#diff-02f7c5a06a2d23d544a07d57af16c7ffb74886469c8844385f51a719e329e6b8 [extract]: https://github.com/vllm-project/vllm/pull/49811/files#diff-b13061cd1be0bc80aaa9fce208fe9128aaaad25b3832c5f1693da1d4e8263f5e [schedfixture]: https://github.com/vllm-project/vllm/pull/53388/files#diff-9eeca590fd99f15621897e559dba39b3ec4e7c2c65ec3c3229711689e008b5f4 [stats]: https://github.com/vllm-project/vllm/pull/52358/files#diff-5823f988fc0264681a80db24ccaba4d364f14394815d83ec1d90944c09f571f0 [offloadM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_offload/config.py [offloadR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/kv_offload/config.py [expertsM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/model_executor/layers/fused_moe/routed_experts.py [expertsR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/model_executor/layers/fused_moe/routed_experts.py [thinkingM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/tokenizers/deepseek_v4.py [thinkingR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/tokenizers/deepseek_v4.py [grammarM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/structured_output/__init__.py [grammarR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/structured_output/__init__.py [proposerM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/spec_decode/extract_hidden_states.py [proposerR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/spec_decode/extract_hidden_states.py [configM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/config/vllm.py [configR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/config/vllm.py [cacheM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/kv_cache_interface.py [blockM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/gpu/block_table.py [blockR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/gpu/block_table.py [mambasrcM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/worker/mamba_utils.py [mambasrcR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/worker/mamba_utils.py [sfatest]: https://github.com/vllm-project/vllm-ascend/blob/b8b230112d9d1edb13b8df2cd4d422074c17d640/tests/e2e/pull_request/four_card/context_parallel/test_accuracy_v2.py [ascglm]: https://github.com/vllm-project/vllm-ascend/pull/15913/files [ascmoon]: https://github.com/vllm-project/vllm-ascend/pull/14068/files [ascpcp]: https://github.com/vllm-project/vllm-ascend/pull/15969/files [ascextract]: https://github.com/vllm-project/vllm-ascend/pull/14699/files [range]: vllm-project/vllm@b2f6858...a97dacb [producer]: https://github.com/vllm-project/vllm/pull/53896/files#diff-80ee7e2a62f9dcfbb8a312dc4e3948557e97ef187290daebbcae1e28596bda29 [schedoutM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/output.py#L282-L292 [schedoutR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/output.py#L252-L265 [schedM]: https://github.com/vllm-project/vllm/blob/a97dacb7106ee49f39f3d1fc6ae1800ff724e01d/vllm/v1/core/sched/scheduler.py#L1354-L1450 [schedR]: https://github.com/vllm-project/vllm/blob/2cf0a6915ce544dc493a0990f2ea38d81601128a/vllm/v1/core/sched/scheduler.py#L1233-L1290 [ascwindow]: https://github.com/vllm-project/vllm-ascend/pull/16120/files - vLLM main: vllm-project/vllm@b2f6858 --------- Signed-off-by: shenzhao <shenzhao9@huawei.com> Co-authored-by: shenzhao <shenzhao9@huawei.com> Signed-off-by: like-0517 <ithwlike@126.com>

gemini-code-assist Bot reviewed Aug 12, 2026

View reviewed changes

nwpu-zxr force-pushed the refactor_connector branch from 7d3d5db to e63d65a Compare August 12, 2026 09:12

github-actions Bot added the module:core label Aug 12, 2026

github-actions Bot added the module:tests label Aug 21, 2026

nwpu-zxr force-pushed the refactor_connector branch from 70e23b5 to a1484c9 Compare August 21, 2026 07:57

recky-c pushed a commit to recky-c/vllm-ascend that referenced this pull request Aug 22, 2026

feat(kv-transfer): support MooncakeConnectorV2 with KVPP (vllm-projec…

24d5b47

…t#14068) Squashed from the 40 commits in upstream PR vllm-project#14068 and rebased onto 26190b4.

wangxiaoteng888 reviewed Sep 2, 2026

View reviewed changes

nwpu-zxr changed the title ~~[Draft][Refactor][P/D] Refactor MooncakeconnectorV1~~ [Feature][Refactor][P/D] Add MooncakeConnectorV2 Sep 7, 2026

nwpu-zxr marked this pull request as ready for review September 7, 2026 09:19

nwpu-zxr requested a review from LCAIZJ as a code owner September 7, 2026 09:19

nwpu-zxr force-pushed the refactor_connector branch from bab558d to 3c05c01 Compare September 7, 2026 15:12

weijinqian0 previously approved these changes Sep 8, 2026

View reviewed changes

nwpu-zxr added 16 commits September 9, 2026 12:02

add mooncake connector v2 base class

9a4fb8f

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add base scheduler worker

70f89c9

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add base worker

b6befac

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add basic worker

18948f6

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add register_kv_caches

ccbcb67

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add scheduler send/recv thread

c1d0327

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add full block ids

9b8b847

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add full-pp transfermetadata

918bc2e

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add worker basic function

1b246d5

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add get_remote_metadata

08b07b8

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add transfer metadata

6186c97

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add merge transfermetadata

36e87c7

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

simplify metadata

bddcaec

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

fix ruff format

12cd4d6

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add kernel block sizes

b867c23

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add remote_tp_layout

f8deee9

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

nwpu-zxr and others added 13 commits September 9, 2026 12:02

add mooncake connector v2 UT

1bd6553

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

fix UT

e414ca6

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add more UT

f000e29

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

fix ut ruff

1f971c0

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add base class UT

930c862

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

support kvpp

cbbb4e3

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add comments & fix mypy

da5aa12

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

support p-kvpp with d-dcp

b9ba3e4

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

fix indexerspec block size

30b6753

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

add block merge

a8af7c4

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

fix ruff

d07686a

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

chore(mooncake): add connector V2 runtime logs

3bd67f3

Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>

support new kv_cache_tensors

5f12fba

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>

nwpu-zxr dismissed weijinqian0’s stale review via 5f12fba September 9, 2026 08:29

nwpu-zxr force-pushed the refactor_connector branch from fdcccf5 to 5f12fba Compare September 9, 2026 08:29

zouyida2052 added the ready-precise run selected e2e test for pr label Sep 9, 2026

weijinqian0 approved these changes Sep 9, 2026

View reviewed changes

weijinqian0 merged commit c5a4d32 into vllm-project:main Sep 9, 2026
39 of 40 checks passed

zhao-stack mentioned this pull request Sep 9, 2026

[Misc][Main2Main] Main2main 0909 #16009

Merged

This was referenced Sep 21, 2026

[Feature](kv_transfer): add MooncakeHeterogeneousPushConnector for V2 architecture kc2608/vllm-ascend#1

Open

[Feature](kv_transfer): add MooncakeHeterogeneousPushConnector for V2 architecture #17077

Open

		src_list.append(local_block_addr + local_inner_offset)
		dst_list.append(remote_block_addr + remote_inner_offset)

		src_list.append(local_base_addr + local_block_id * local_block_stride)
		dst_list.append(remote_base_addr + remote_block_id * remote_block_stride)

		token_ids = request.prompt_token_ids or []
		actual = self._state_prefill_token_count(len(token_ids))

		prompt_token_ids = request.prompt_token_ids or []
		prompt_len = len(prompt_token_ids)

	prompt_token_ids = request.prompt_token_ids or []
	prompt_len = len(prompt_token_ids)
	prompt_len = request.num_prompt_tokens


		logger.info("Initializing Mooncake Scheduler %s", engine_id)

		def _needs_prefill_token_truncation(self) -> bool:

Conversation

nwpu-zxr commented Aug 12, 2026 • edited by github-actions Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

Uh oh!

gemini-code-assist Bot commented Aug 12, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

github-actions Bot commented Aug 12, 2026

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot Aug 12, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiaoteng888 Sep 2, 2026

Choose a reason for hiding this comment

Uh oh!

nwpu-zxr Sep 9, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

nwpu-zxr commented Aug 12, 2026 •

edited by github-actions Bot

Loading