[Refactor] cache cos/sin in mla & remove parameter model in builder.#5277
Merged
weijinqian0 merged 25 commits intovllm-project:mainfrom Dec 28, 2025
Merged
[Refactor] cache cos/sin in mla & remove parameter model in builder.#5277weijinqian0 merged 25 commits intovllm-project:mainfrom
weijinqian0 merged 25 commits intovllm-project:mainfrom
Conversation
added 2 commits
December 23, 2025 13:32
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request effectively resolves a bug in xlite caused by an attempt to access a non-existent attribute query_start_loc_cpu on AscendMetadata. The fix correctly moves the calculation of query_lens into the AscendAttentionMetadataBuilder, storing the result in AscendMetadata. This not only fixes the AttributeError but also centralizes the logic, improving code structure. The changes are accurate and well-implemented.
Contributor
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
weijinqian0
changed the title
weijinqian0
changed the title
added 3 commits
December 24, 2025 15:54
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
weijinqian0
added
ready
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
wangxiyuan
approved these changes
Dec 26, 2025
Collaborator
|
let's merge this after 0.13.0 released |
845473182
pushed a commit
to 845473182/vllm-ascend
that referenced
this pull request
Dec 29, 2025
…to eplb_refactor * 'main' of https://github.com/vllm-project/vllm-ascend: (46 commits) [Feature] Support to use fullgraph with eagle (vllm-project#5118) [EPLB][refactor] Modification of the initialization logic for expert_map and log2phy（depend on pr5285） (vllm-project#5311) [Refactor]6/N Extract common code of class AscendMLAImpl (vllm-project#5314) [Refactor] cache cos/sin in mla & remove parameter model in builder. (vllm-project#5277) update vllm pin to 12.27 (vllm-project#5412) [ReleaseNote] Add release note for v0.13.0rc1 (vllm-project#5334) [Bugfix] Correctly handle the output shape in multimodal attention (vllm-project#5443) Fix nightly (vllm-project#5413) [bugfix] fix typo of _skip_all_reduce_across_dp_group (vllm-project#5435) [Doc]modify pcp tutorial doc (vllm-project#5440) [Misc] fast fail for exiting if tools/install_flash_infer_attention_score_ops_a2.sh (vllm-project#5422) [Doc] Update DeepSeek V3.1/R1 2P1D doc (vllm-project#5387) [DOC]Fix model weight download links (vllm-project#5436) [Doc] Modify DeepSeek-R1/V3.1 documentation (vllm-project#5426) Revert "[feat] enable hierarchical mc2 ops on A2 by default (vllm-project#5300)" (vllm-project#5434) [Bugfix] fix greedy temperature detection (vllm-project#5417) [doc] Update Qwen3-235B doc for reproducing latest performance (vllm-project#5323) [feat] enable hierarchical mc2 ops on A2 by default (vllm-project#5300) [Doc] delete environment variable HCCL_OP_EXPANSION_MODE in DeepSeekV3.1/R1 (vllm-project#5419) [Doc] add long_sequence feature user guide (vllm-project#5343) ...
Mercykid-bash
pushed a commit
to Mercykid-bash/vllm-ascend
that referenced
this pull request
Dec 29, 2025
…llm-project#5277) RFC: vllm-project#4629 1. Cache cos/sin in mla 2. AttentionBuilder inherits from the original class of vllm. version: release/v0.13.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: weijinqian_v1 <weijinqian@huawei.com> Co-authored-by: weijinqian_v1 <weijinqian@huawei.com> Signed-off-by: Che Ruan <cr623@ic.ac.uk>
845473182
pushed a commit
to 845473182/vllm-ascend
that referenced
this pull request
Dec 31, 2025
…to FIA_rebase * 'main' of https://github.com/vllm-project/vllm-ascend: (88 commits) [1/N] Refactor nightly test structure (vllm-project#5479) Docs: Remove deprecated --task parameter for embedding models (vllm-project#5257) Revert "moe_gating_top_k" (vllm-project#5512) [Doc] Fix issue link for 0.12.0 (vllm-project#5500) [CI]update triton ascend version (vllm-project#5392) moe_gating_top_k (vllm-project#5271) [refactor] refactor model runner capture model (vllm-project#5230) Update corresponding vllm commit ID to 12 29 (vllm-project#5475) [Kernel]update csrc cmakelist for open-source cann (vllm-project#5458) [OP] add custom op aclnnMoeInitRoutingCustom (vllm-project#5251) [Refactor][EAGLE] 1/N delete __init__ in mtp_proposer (vllm-project#5176) [Refactor][Triton] Move reject sample triton kernels into ops/triton (vllm-project#5324) [Feature] support eager mode in model runner v2 (vllm-project#5210) [feature] fia support sliding windows (vllm-project#5239) Optimize some rejectsampler functions to make npu op launch non-blocking (vllm-project#4587) [Feature] Support to use fullgraph with eagle (vllm-project#5118) [EPLB][refactor] Modification of the initialization logic for expert_map and log2phy（depend on pr5285） (vllm-project#5311) [Refactor]6/N Extract common code of class AscendMLAImpl (vllm-project#5314) [Refactor] cache cos/sin in mla & remove parameter model in builder. (vllm-project#5277) update vllm pin to 12.27 (vllm-project#5412) ...
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Feb 28, 2026
…llm-project#5277) RFC: vllm-project#4629 1. Cache cos/sin in mla 2. AttentionBuilder inherits from the original class of vllm. version: release/v0.13.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: weijinqian_v1 <weijinqian@huawei.com> Co-authored-by: weijinqian_v1 <weijinqian@huawei.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
maoxx241
pushed a commit
to maoxx241/vllm-ascend
that referenced
this pull request
Mar 2, 2026
…llm-project#5277) RFC: vllm-project#4629 1. Cache cos/sin in mla 2. AttentionBuilder inherits from the original class of vllm. version: release/v0.13.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: weijinqian_v1 <weijinqian@huawei.com> Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Mar 4, 2026
…llm-project#5277) RFC: vllm-project#4629 1. Cache cos/sin in mla 2. AttentionBuilder inherits from the original class of vllm. version: release/v0.13.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: weijinqian_v1 <weijinqian@huawei.com> Co-authored-by: weijinqian_v1 <weijinqian@huawei.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
RFC: #4629
version: release/v0.13.0