Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
118 Open 1,079 Closed
118 Open 1,079 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Update README.zh.md to fix typo documentation Improvements or additions to documentation
#1758 opened Jul 12, 2025 by Yikun Loading…
[bugfix] fix deepseek bug when tp_size == 1 module:ops
#1755 opened Jul 11, 2025 by zzzzwwjj Loading…
[0.9.1][Perf] Port MLA multistream optimazition and prefetch to v0.9.1 module:core
#1750 opened Jul 11, 2025 by whx-sjtu Loading…
[V0.9.1] torchair_graph bugfix when chunked_prefill is true
#1748 opened Jul 11, 2025 by fems14 Loading…
[v0.9.1] fix async pullkv determin
#1746 opened Jul 11, 2025 by ganyi1996ppo Loading…
[V0.9.1] Add support for flashcomm_v1 in Qwen2.5 module:core module:ops
#1745 opened Jul 11, 2025 by rjg-lyh Loading…
flashcomm3 multi stream of moe layer merge-conflicts module:core module:ops module:quantization
#1744 opened Jul 11, 2025 by wyhhyw123 Loading…
1
[Platform] Add support for Altlas A3 series ci/build module:core
#1740 opened Jul 11, 2025 by wxsIcey Loading…
2
Optimization of TP4 Parallelism in DeepSeek MLP Dense Layers
#1738 opened Jul 11, 2025 by zhanghw0354 Loading…
[Doc] Add model costomization doc documentation Improvements or additions to documentation
#1737 opened Jul 11, 2025 by shen-shanshan Loading…
[2/N] Enable shellcheck and pymarkdown for lint system documentation Improvements or additions to documentation module:tests module:tools
#1735 opened Jul 11, 2025 by Potabk Loading…
[Test] Remove VLLM_USE_V1 in example and tests module:tests
#1733 opened Jul 11, 2025 by wangxiyuan Loading…
1
[Perf] Reduce memory usage by splitting tokens in fused_experts documentation Improvements or additions to documentation module:core module:ops module:quantization module:tests ready read for review
#1729 opened Jul 10, 2025 by ApsarasX Loading…
2
[V0.9.1] add support for flashcomm2 in qwen3 module:core
#1726 opened Jul 10, 2025 by David9857 Loading…
2
[BUGFIX] [v0.9.1-dev] Obtain the NPU ID of non-consecutive NPU cards
#1724 opened Jul 10, 2025 by yangqinghao-cmss Loading…
1
[V0.9.1] optimize rope in qwen3 module:ops module:tests
#1719 opened Jul 10, 2025 by David9857 Loading…
1
add moe operation module:tests
#1709 opened Jul 9, 2025 by shiyuan680 Loading…
[v0.9.1]add rot_pos_emb()/get_window_index()/_process_image_input() to qwen2.5_vl_without_padding
#1705 opened Jul 9, 2025 by zheliuyu Loading…
1
[V0.9.1] Replace FA interface with FA_V2 to optimize perf in SelfAttention
#1701 opened Jul 9, 2025 by rjg-lyh Loading…
[0.9.1]feat: Qwen3-dense model support dual-batch overlap(dbo)
#1699 opened Jul 9, 2025 by ZhaoJiangJiang Loading…
[WIP] dynamic eplb module:core module:ops module:quantization
#1697 opened Jul 9, 2025 by wanghanqingLYT Loading…
1
support fa3 quant for v0.9.1-dev merge-conflicts module:quantization module:tests
#1695 opened Jul 9, 2025 by 22dimensions Loading…
1
[0.9.1][PD] Added support for delay-free blocks in prefill nodes
#1691 opened Jul 9, 2025 by underfituu Loading…
[WIP][Prefill Performance] Parallel Strategy Optimizations (VRAM-for-Speed Tradeoff) merge-conflicts module:ops module:quantization
#1687 opened Jul 9, 2025 by SlightwindSec Loading…
1
[V0 Deprecation] Remove V0 prompt adapter merge-conflicts
#1683 opened Jul 9, 2025 by shen-shanshan Loading…
1
ProTip! no:milestone will show everything without a milestone.