[Main2Main] Upgrade vllm commit to 0123 by Meihan-chen · Pull Request #6169 · vllm-project/vllm-ascend

Meihan-chen · 2026-01-23T02:30:47Z

What this PR does / why we need it?

✅ Upgrade vllm commit to: 0115 (8471b27)
Modify import paths due to the refactors：
[Model Runner V2] Refactor Sampler vllm#32245
[4/N][Attention] Move MLA common to model_executor vllm#32060
Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913
✅Upgrade vllm commit to: 0119 (9a1f16d)
Fix WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker' due to [TPU][Core] Enable Pipeline Parallelism on TPU backend vllm#28506
Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569
✅Upgrade vllm commit to: 0120(148117e)
1. Add skip_compiled param in set_forward_context due to [Core] Whisper support torch.compile vllm#30385
2. Modify tests/ut/spec_decode/test_eagle_proposer.py due to feat: spec decode with draft models vllm#24322
  change self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size
3. Modify UT import paths due to the refactors：[4/N][Attention] Move MLA common to model_executor vllm#32060
  Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946
✅Upgrade vllm commit to: 0121(f23fb5a)
1. vLLM switched uses_mrope from target to draft model config, making positions/mrope_positions mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing draft_model_config.uses_mrope. Added qwen3 vision language moe support for speculative decoding vllm#32048
2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor [Misc] Remove pad_for_cudagraphs from config vllm#30143
3. Remove unused maybe_setup_kv_connector due to [Cleanup] Remove unused KVConnectorModelRunnerMixin methods vllm#32077
  Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834
✅Upgrade vllm commit to: 0122(8ebf271)
Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to [MoE Refactor] Oracle Select FP8+NVFP4 Kernels In Priority vllm#32414
Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054
✅Upgrade vllm commit to: 0123(dc917cc)
Setting temperature=0.0 due to the removal of the default temperature value in [Benchmark] Don't default to temperature==0 in vllm bench serve vllm#32723
Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875

Does this PR introduce any user-facing change?

How was this patch tested?

vLLM version: v0.14.0
vLLM main: vllm-project/vllm@d682094

github-actions · 2026-01-23T02:31:00Z

👋 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

This pull request upgrades the vLLM dependency to a newer commit and adapts the codebase to the corresponding upstream changes. The modifications span across documentation, tests, and core logic, primarily addressing API changes in vLLM. Key adaptations include conditional imports for moved classes like MLACommonMetadataBuilder and AttentionMetadataBuilder, updated function signatures for context management and worker process creation, and support for new features like M-RoPE. The changes appear to be correctly implemented for version compatibility and maintain functionality. The codebase adaptations are thorough and well-executed, with no high or critical severity issues found.

github-actions · 2026-01-24T14:12:35Z

This pull request has conflicts, please resolve those before we can evaluate the pull request.

Signed-off-by: wjunLu <wjunlu217@gmail.com>

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

Meihan-chen · 2026-01-26T10:41:37Z

All checks have passed in https://github.com/vllm-project/vllm-ascend/actions/runs/21348540836/job/61440604090
https://github.com/vllm-project/vllm-ascend/actions/runs/21353410481/job/61455937068

wangxiyuan · 2026-01-26T11:13:57Z

    total_steps = max_tokens + 1  # this includes the 1 and 2 above
-    expected_exec_model = (total_steps + 1) * dp_size
+    # vllm default enables Async scheduler, this will take 1 more steps
+    expected_exec_model = (total_steps + 1 + 1) * dp_size


0.14.0 enable async scheduler already. why it's fine before?

To adapt to previous upgrades, it was set to false in https://github.com/vllm-project/vllm-ascend/pull/6169/changes/BASE..181a3a373cc9e8f37908c3d14ae83d60dd8b4f6e#diff-0e3dd1c713072facdea0241f1b908c2121957baf6f0400fd71f9b8224f2c98d1L112； this config should remov when the VLLM version is >= 0.14.0.

wangxiyuan · 2026-01-26T11:14:42Z

    "random_input_len": 128,
    "max_concurrency": 40,
    "random_output_len": 100,
+    "temperature": 0.0,


I think we should add it to benchamark module? @wxsIcey

wangxiyuan · 2026-01-26T11:15:52Z

            global_start_rank = self.local_world_size * self.parallel_config.node_rank_within_dp
            for local_rank in range(self.local_world_size):
                global_rank = global_start_rank + local_rank
+                is_driver_worker = self._is_driver_worker(global_rank)


is this change work with 0.14.0?

is_driver_worker is vllm-ascend's own make_worker_process method which always accepts this parameter, while AscendWorkerProc conditionally passes it to vllm's native WorkerProc.init which only accepts it in newer versions，so only https://github.com/vllm-project/vllm-ascend/pull/6169/changes/BASE..181a3a373cc9e8f37908c3d14ae83d60dd8b4f6e#diff-b25d0746a873edc4bc07a475dd926377fdda5e51a437fc329123eea9202cfdaaR181 needs version checking.

wangxiyuan · 2026-01-26T11:17:12Z

 import torch
 from vllm.triton_utils import tl, triton
-from vllm.v1.worker.gpu.sample.metadata import SamplingMetadata
+from vllm.v1.sample.metadata import SamplingMetadata


work with v0.14.0?

…to qwen3next_rebase * 'main' of https://github.com/vllm-project/vllm-ascend: (86 commits) [refactor] refactor excute_model and _dymmy_run method (vllm-project#6043) [Refactor] profiler config optimze (vllm-project#6141) [Graph][Fusion] Add MatmulAllReduceAddRMSNorm graph fusion for npugraph_ex. (vllm-project#6006) [UT]: refactoring 310p ops ut (vllm-project#6296) [Refact.]: refactoring 310p-kv cache allocator, align with main branch (vllm-project#6270) [Misc] Removes unnecessary graph size re-initialization (vllm-project#6280) [Main2Main] Upgrade vllm commit to 0123 (vllm-project#6169) [BugFix] Fix wheel package build workflow (vllm-project#6276) [CI][BugFix] Qwen3-Next nightly test fix. (vllm-project#6247) [Doc] quick fix for vllm-ascend version (vllm-project#6278) [Community] Nominate whx-sjtu as maintainer (vllm-project#6268) [Lint] Fix mypy issue to make CI happy (vllm-project#6272) BugFix: Fix moe_load accumulation error in ACL graph mode (vllm-project#6182) [Patch] Remove the patch of ECExampleConnector (vllm-project#5976) [Bugfix] Fix PP+PCP and PP+flashcomm1 bugs (vllm-project#5416) [Feat] proxy delay to remove instances (vllm-project#5934) [CI] Add workfolw_dispatch for nightly image build (vllm-project#6269) [bugfix][npugraph_ex]fix static kernel uninstall issue (vllm-project#6128) [Doc] 310P Documents update (vllm-project#6246) [Feature] Mooncake connector get remote ptp size (vllm-project#5822) ...

### What this PR does / why we need it? 1. ✅ Upgrade vllm commit to: 0115 (8471b27) Modify import paths due to the refactors： vllm-project/vllm#32245 vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913 2. ✅Upgrade vllm commit to: 0119 (9a1f16d) Fix `WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker'` due to vllm-project/vllm#28506 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569 3. ✅Upgrade vllm commit to: 0120(148117e) 1. Add `skip_compiled` param in `set_forward_context` due to vllm-project/vllm#30385 2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to vllm-project/vllm#24322 change `self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size` 3. Modify UT import paths due to the refactors：vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946 4. ✅Upgrade vllm commit to: 0121(f23fb5a) 1. vLLM switched `uses_mrope` from target to draft model config, making `positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing `draft_model_config.uses_mrope`. vllm-project/vllm#32048 2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor vllm-project/vllm#30143 3. Remove unused `maybe_setup_kv_connector` due to vllm-project/vllm#32077 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834 6. ✅Upgrade vllm commit to: 0122(8ebf271) Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to vllm-project/vllm#32414 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054 8. ✅Upgrade vllm commit to: 0123(dc917cc) Setting temperature=0.0 due to the removal of the default temperature value in vllm-project/vllm#32723 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: vllm-project/vllm@d682094 --------- Signed-off-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: wjunLu <wjunlu217@gmail.com>

### What this PR does / why we need it? 1. ✅ Upgrade vllm commit to: 0115 (8471b27) Modify import paths due to the refactors： vllm-project/vllm#32245 vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913 2. ✅Upgrade vllm commit to: 0119 (9a1f16d) Fix `WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker'` due to vllm-project/vllm#28506 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569 3. ✅Upgrade vllm commit to: 0120(148117e) 1. Add `skip_compiled` param in `set_forward_context` due to vllm-project/vllm#30385 2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to vllm-project/vllm#24322 change `self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size` 3. Modify UT import paths due to the refactors：vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946 4. ✅Upgrade vllm commit to: 0121(f23fb5a) 1. vLLM switched `uses_mrope` from target to draft model config, making `positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing `draft_model_config.uses_mrope`. vllm-project/vllm#32048 2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor vllm-project/vllm#30143 3. Remove unused `maybe_setup_kv_connector` due to vllm-project/vllm#32077 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834 6. ✅Upgrade vllm commit to: 0122(8ebf271) Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to vllm-project/vllm#32414 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054 8. ✅Upgrade vllm commit to: 0123(dc917cc) Setting temperature=0.0 due to the removal of the default temperature value in vllm-project/vllm#32723 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: vllm-project/vllm@d682094 --------- Signed-off-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: momochenchuw <chenchuw@huawei.com>

### What this PR does / why we need it? 1. ✅ Upgrade vllm commit to: 0115 (8471b27) Modify import paths due to the refactors： vllm-project/vllm#32245 vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913 2. ✅Upgrade vllm commit to: 0119 (9a1f16d) Fix `WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker'` due to vllm-project/vllm#28506 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569 3. ✅Upgrade vllm commit to: 0120(148117e) 1. Add `skip_compiled` param in `set_forward_context` due to vllm-project/vllm#30385 2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to vllm-project/vllm#24322 change `self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size` 3. Modify UT import paths due to the refactors：vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946 4. ✅Upgrade vllm commit to: 0121(f23fb5a) 1. vLLM switched `uses_mrope` from target to draft model config, making `positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing `draft_model_config.uses_mrope`. vllm-project/vllm#32048 2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor vllm-project/vllm#30143 3. Remove unused `maybe_setup_kv_connector` due to vllm-project/vllm#32077 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834 6. ✅Upgrade vllm commit to: 0122(8ebf271) Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to vllm-project/vllm#32414 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054 8. ✅Upgrade vllm commit to: 0123(dc917cc) Setting temperature=0.0 due to the removal of the default temperature value in vllm-project/vllm#32723 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: vllm-project/vllm@d682094 --------- Signed-off-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

### What this PR does / why we need it? 1. ✅ Upgrade vllm commit to: 0115 (8471b27) Modify import paths due to the refactors： vllm-project/vllm#32245 vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913 2. ✅Upgrade vllm commit to: 0119 (9a1f16d) Fix `WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker'` due to vllm-project/vllm#28506 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569 3. ✅Upgrade vllm commit to: 0120(148117e) 1. Add `skip_compiled` param in `set_forward_context` due to vllm-project/vllm#30385 2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to vllm-project/vllm#24322 change `self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size` 3. Modify UT import paths due to the refactors：vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946 4. ✅Upgrade vllm commit to: 0121(f23fb5a) 1. vLLM switched `uses_mrope` from target to draft model config, making `positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing `draft_model_config.uses_mrope`. vllm-project/vllm#32048 2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor vllm-project/vllm#30143 3. Remove unused `maybe_setup_kv_connector` due to vllm-project/vllm#32077 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834 6. ✅Upgrade vllm commit to: 0122(8ebf271) Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to vllm-project/vllm#32414 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054 8. ✅Upgrade vllm commit to: 0123(dc917cc) Setting temperature=0.0 due to the removal of the default temperature value in vllm-project/vllm#32723 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: vllm-project/vllm@d682094 --------- Signed-off-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: wjunLu <wjunlu217@gmail.com>

### What this PR does / why we need it? 1. ✅ Upgrade vllm commit to: 0115 (8471b27) Modify import paths due to the refactors： vllm-project/vllm#32245 vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913 2. ✅Upgrade vllm commit to: 0119 (9a1f16d) Fix `WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker'` due to vllm-project/vllm#28506 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569 3. ✅Upgrade vllm commit to: 0120(148117e) 1. Add `skip_compiled` param in `set_forward_context` due to vllm-project/vllm#30385 2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to vllm-project/vllm#24322 change `self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size` 3. Modify UT import paths due to the refactors：vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946 4. ✅Upgrade vllm commit to: 0121(f23fb5a) 1. vLLM switched `uses_mrope` from target to draft model config, making `positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing `draft_model_config.uses_mrope`. vllm-project/vllm#32048 2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor vllm-project/vllm#30143 3. Remove unused `maybe_setup_kv_connector` due to vllm-project/vllm#32077 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834 6. ✅Upgrade vllm commit to: 0122(8ebf271) Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to vllm-project/vllm#32414 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054 8. ✅Upgrade vllm commit to: 0123(dc917cc) Setting temperature=0.0 due to the removal of the default temperature value in vllm-project/vllm#32723 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: vllm-project/vllm@d682094 --------- Signed-off-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

### What this PR does / why we need it? 1. ✅ Upgrade vllm commit to: 0115 (8471b27) Modify import paths due to the refactors： vllm-project/vllm#32245 vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913 2. ✅Upgrade vllm commit to: 0119 (9a1f16d) Fix `WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker'` due to vllm-project/vllm#28506 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569 3. ✅Upgrade vllm commit to: 0120(148117e) 1. Add `skip_compiled` param in `set_forward_context` due to vllm-project/vllm#30385 2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to vllm-project/vllm#24322 change `self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size` 3. Modify UT import paths due to the refactors：vllm-project/vllm#32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946 4. ✅Upgrade vllm commit to: 0121(f23fb5a) 1. vLLM switched `uses_mrope` from target to draft model config, making `positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing `draft_model_config.uses_mrope`. vllm-project/vllm#32048 2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor vllm-project/vllm#30143 3. Remove unused `maybe_setup_kv_connector` due to vllm-project/vllm#32077 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834 6. ✅Upgrade vllm commit to: 0122(8ebf271) Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to vllm-project/vllm#32414 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054 8. ✅Upgrade vllm commit to: 0123(dc917cc) Setting temperature=0.0 due to the removal of the default temperature value in vllm-project/vllm#32723 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: vllm-project/vllm@d682094 --------- Signed-off-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: wjunLu <wjunlu217@gmail.com>

Meihan-chen requested review from LCAIZJ, MengqingCao, Yikun, wangxiyuan and weijinqian0 as code owners January 23, 2026 02:30

github-actions Bot added documentation Improvements or additions to documentation ci/build module:tests module:core labels Jan 23, 2026

gemini-code-assist Bot reviewed Jan 23, 2026

View reviewed changes

wjunLu added ready read for review ready-for-test start test by label for PR labels Jan 23, 2026

Meihan-chen force-pushed the main0123 branch 4 times, most recently from 90a9aa2 to 8b3af93 Compare January 23, 2026 09:11

github-actions Bot added the merge-conflicts label Jan 24, 2026

wjunLu and others added 11 commits January 26, 2026 09:51

[Main2Main] Upgrade vllm commit to 0116

3607a5e

Signed-off-by: wjunLu <wjunlu217@gmail.com>

[Main2Main] Update vllm commit to 0119

b4b98d7

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

update patch_multiproc_executor

be6f42e

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

fix 0120 bug

3fe807e

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

[Main2Main] Upgrade vllm commit to 0121

5e8062e

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

fix main0121

2b1226b

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

fix maybe_setup_kv_connector

0b3bbf7

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

fix bs_to_padded_graph_size

717bd3b

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

[Main2Main] Upgrade vllm commit to 0122

2ec8989

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

fix FusedMoEParallelConfig

55cfe8b

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

[Main2Main] Upgrade vllm commit to 0123

f4853bc

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

Meihan-chen force-pushed the main0123 branch from 8b3af93 to e2f6330 Compare January 26, 2026 02:03

github-actions Bot removed the merge-conflicts label Jan 26, 2026

Meihan-chen force-pushed the main0123 branch 4 times, most recently from 25eeebc to 30f3057 Compare January 26, 2026 06:24

fix test_qwen3_performance by #32723

5dd5f41

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

Meihan-chen force-pushed the main0123 branch 2 times, most recently from d8c28b9 to 02fcce2 Compare January 26, 2026 09:44

update lint commit

181a3a3

Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>

Meihan-chen force-pushed the main0123 branch from 02fcce2 to 181a3a3 Compare January 26, 2026 09:55

wangxiyuan reviewed Jan 26, 2026

View reviewed changes

wangxiyuan merged commit fea197a into vllm-project:main Jan 27, 2026
20 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Main2Main] Upgrade vllm commit to 0123#6169

[Main2Main] Upgrade vllm commit to 0123#6169
wangxiyuan merged 13 commits intovllm-project:mainfrom
Meihan-chen:main0123

Meihan-chen commented Jan 23, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jan 23, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

github-actions Bot commented Jan 24, 2026

Uh oh!

Meihan-chen commented Jan 26, 2026

Uh oh!

wangxiyuan Jan 26, 2026

Uh oh!

Meihan-chen Jan 26, 2026

Uh oh!

wangxiyuan Jan 26, 2026

Uh oh!

wangxiyuan Jan 26, 2026

Uh oh!

Meihan-chen Jan 26, 2026

Uh oh!

wangxiyuan Jan 26, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

Meihan-chen commented Jan 23, 2026 • edited 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!

github-actions Bot commented Jan 23, 2026

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

github-actions Bot commented Jan 24, 2026

Uh oh!

Meihan-chen commented Jan 26, 2026

Uh oh!

wangxiyuan Jan 26, 2026

Choose a reason for hiding this comment

Uh oh!

Meihan-chen Jan 26, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiyuan Jan 26, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiyuan Jan 26, 2026

Choose a reason for hiding this comment

Uh oh!

Meihan-chen Jan 26, 2026

Choose a reason for hiding this comment

Uh oh!

wangxiyuan Jan 26, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Meihan-chen commented Jan 23, 2026 •

edited

Loading