Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
39 Open 428 Closed
39 Open 428 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[WIP]Add Func: npugraph_batch_size auto-adjust to different model
#713 opened Apr 28, 2025 by chris668899 Loading…
V1 parallel fix: bug fix to enable DP in V1 module:ops
#710 opened Apr 28, 2025 by HanlinDu • Draft
1
[WIP][Build][0.7.3] Integrate MindIE Turbo into vLLM Ascend documentation Improvements or additions to documentation
#708 opened Apr 28, 2025 by MengqingCao Loading…
1
Optimize qwen2_vl and qwen2_5_vl module:ops
#701 opened Apr 28, 2025 by zouyida2052 Loading…
[Disaggregated Prefill][WIP] P2P Disaggregated Prefill based on llm_datadist
#694 opened Apr 28, 2025 by whx-sjtu Loading…
8
[MISC] Clean up torch_npu module:core module:ops module:quantization module:tests
#688 opened Apr 28, 2025 by wangxiyuan Loading…
[Feature] Impl the connector based on the llmdatadist for v1 module:core
#684 opened Apr 27, 2025 by jianzs Loading…
1 of 5 tasks
feat: performance optimization for deepseek module:quantization
#683 opened Apr 27, 2025 by zzzzwwjj Loading…
3
[Bugfix] Fix early return in CustomDeepseekV2MoE.forward during profile_run
#682 opened Apr 27, 2025 by ApsarasX Loading…
1
update chunk prefill torch module:ops module:tests
#679 opened Apr 27, 2025 by ttanzhiqiang Loading…
2
[WIP] Add support for custom DeepSeek modelling in ACL Graph mode module:core module:ops
#677 opened Apr 27, 2025 by yiz-liu Loading…
[CI] Add nightly CI
#668 opened Apr 27, 2025 by Potabk Loading…
2
Test Rm lib path documentation Improvements or additions to documentation
#667 opened Apr 27, 2025 by Yikun • Draft
test original ld documentation Improvements or additions to documentation
#666 opened Apr 27, 2025 by Yikun • Draft
[Feature] Enable disaggregated prefill functionality for v0 module:core module:tests
#658 opened Apr 25, 2025 by jianzs Loading…
4
Adjust KV cache shape for compatibility with updated APIs for graph mode ci/build
#657 opened Apr 25, 2025 by linfeng-yuan Loading…
[MISC] fix format check error documentation Improvements or additions to documentation module:ops module:tests module:tools
#654 opened Apr 25, 2025 by wangxiyuan Loading…
1
[CI] Add qwen2.5-vl v1 test module:tests
#653 opened Apr 25, 2025 by Potabk Loading…
[UT]Compat with cuda and npu module:core
#646 opened Apr 24, 2025 by ponix-j Loading…
1
[Doc] Add benchmark guide documentation Improvements or additions to documentation
#635 opened Apr 23, 2025 by Potabk Loading…
16
[CI] Add deepseek-v2-lite test module:tests
#631 opened Apr 23, 2025 by Potabk Loading…
[Misc] format patch to make the code clear module:core module:quantization
#613 opened Apr 22, 2025 by wangxiyuan Loading…
5
[Platform] format platform to make it more clear module:core
#610 opened Apr 22, 2025 by wangxiyuan Loading…
5
[Perf] Deepseekv3 performance optimization for eager mode module:core module:ops
#598 opened Apr 21, 2025 by ganyi1996ppo Loading…
13
[Bugfix] Fix the bug of torch_npu that raising segment fault when enable pin_memory while creating a tensor module:core
#597 opened Apr 21, 2025 by shen-shanshan Loading…
10
ProTip! What’s not been updated in a month: updated:<2025-03-28.