Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
38 Open 484 Closed
38 Open 484 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

bugfix for qwen2_5_vl
#805 opened May 10, 2025 by zouyida2052 Loading…
[Enhancement] Add padding for ACL Graph and refactor graph batch size module:core
#803 opened May 9, 2025 by yiz-liu Loading…
add V1 Engine LoRA support
#801 opened May 9, 2025 by jesse996 Loading…
1
add custom ascendc kernel vocabparallelembedding module:tests
#796 opened May 8, 2025 by ttanzhiqiang Loading…
1
[P/D][DP] Upgrade pd proxy to support both prefill and decode instances in disaggregated-prefill. module:core
#794 opened May 8, 2025 by whx-sjtu Loading…
2
[Benchmark] Add qwen2.5 and qwen2.5-vl to benchmarks documentation Improvements or additions to documentation
#792 opened May 8, 2025 by Potabk Loading…
1
[bugfix] DP accuracy issue fix
#791 opened May 8, 2025 by ganyi1996ppo Loading…
feat: support torchair graph mode in v1 engine module:core
#789 opened May 8, 2025 by NeverRaR Loading…
1
[CI/UT] Fix the default value of block_size in VllmRunner to None module:tests
#783 opened May 7, 2025 by rjg-lyh Loading…
add workflow to build and release wheel ci/build module:tools
#775 opened May 7, 2025 by celestialli Loading…
1
[CI] Add accuracy test for Qwen2.5-VL-3B-Instruct module:tests
#766 opened May 6, 2025 by hfadzxy Loading…
[V1][Structured Output] Enable Speculative Decoding with Structured Outputs
#751 opened May 5, 2025 by shen-shanshan • Draft
Re-enable Speculative Decode test
#748 opened May 2, 2025 by Yikun • Draft
[Attention][Kernel]moe support for llama4 and mllama4 module:ops
#740 opened Apr 30, 2025 by cxcxflying Loading…
5
Add qwen2.5 vl multimodal feature for vllm-ascend v1 module:tests
#736 opened Apr 30, 2025 by RookieChenTaoYu Loading…
3
Add quickstart doctest documentation Improvements or additions to documentation module:tests
#730 opened Apr 29, 2025 by Yikun • Draft
3
fix indents in model runner
#722 opened Apr 29, 2025 by zhentaocc Loading…
2
V1 parallel fix: bug fix to enable DP in V1 module:core module:ops
#710 opened Apr 28, 2025 by HanlinDu Loading…
8
[Feature] Impl the connector based on the llmdatadist for v1 module:core
#684 opened Apr 27, 2025 by jianzs Loading…
1 of 5 tasks
8
update chunk prefill torch module:ops module:tests
#679 opened Apr 27, 2025 by ttanzhiqiang Loading…
9
[WIP] Add support for custom DeepSeek modelling in ACL Graph mode module:core module:ops
#677 opened Apr 27, 2025 by yiz-liu Loading…
2
[Feature] Enable disaggregated prefill functionality for v0 module:core module:tests
#658 opened Apr 25, 2025 by jianzs Loading…
5
Adjust KV cache shape for compatibility with updated APIs for graph mode ci/build
#657 opened Apr 25, 2025 by linfeng-yuan Loading…
5
[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
ProTip! Filter pull requests by the default branch with base:main.