Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
166 Open 1,369 Closed
166 Open 1,369 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

enable mm allreduce test
#2192 opened Aug 4, 2025 by Ronald1995 Loading…
[bugfix] fix gd or apc or fc run error when ascend_…
#2190 opened Aug 4, 2025 by MrZoloft Loading…
2
[Bugfix][CI] Update ModelRunnerOutput Params to Sync Upstream Changes
#2189 opened Aug 4, 2025 by shen-shanshan Loading…
2
Add release note for v0.9.1rc2 documentation Improvements or additions to documentation
#2188 opened Aug 4, 2025 by Yikun • Draft
5
SwiftBalancer Zero OverHead Expert Movement module:core module:ops module:quantization
#2186 opened Aug 4, 2025 by raindaywhu Loading…
1
[WIP]support lmhead tp module:core
#2185 opened Aug 4, 2025 by Angazenn Loading…
1
[BugFix] Fix the bug that qwen3 moe doesn't work with EP accuracy-test enable all accuracy test for PR module:ops ready-for-test start test by label for PR
#2183 opened Aug 4, 2025 by wangxiyuan Loading…
2
[Bugfix] Fix broken CI accuracy-test enable all accuracy test for PR module:tests ready-for-test start test by label for PR vllm-break
#2181 opened Aug 3, 2025 by Potabk Loading…
2
[FEATURE][0.9.1][MTP] Support MTP > 1
#2180 opened Aug 2, 2025 by 1092626063 Loading…
3 of 6 tasks
[0.9.1]remove chunked_prefill_for_mla documentation Improvements or additions to documentation module:core module:ops
#2177 opened Aug 2, 2025 by fems14 Loading…
[Bugfix][PD] Auto-clear producer KV cache if no pull notification module:core
#2174 opened Aug 2, 2025 by underfituu Loading…
2
[main][Feature] Support deepseek w4a8 quantization module:quantization module:tests
#2172 opened Aug 1, 2025 by kunpengW-code Loading…
2
[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. module:core module:ops module:quantization
#2167 opened Aug 1, 2025 by lidenghui1110 Loading…
1
feat: add mtp ut case module:tests
#2166 opened Aug 1, 2025 by ZhaoJiangJiang Loading…
2
[Doc][PD] Restore the default configuration items in examples/disaggregate_prefill_v1/README.md documentation Improvements or additions to documentation
#2165 opened Aug 1, 2025 by underfituu Loading…
1
Refactormc2 module:ops
#2164 opened Aug 1, 2025 by momo609 Loading…
2
Fix accuracy test config --config-list-file accuracy-test enable all accuracy test for PR module:tests ready-for-test start test by label for PR
#2163 opened Aug 1, 2025 by wxsIcey Loading…
2
[Misc] Support kimi-k2-w8a8 documentation Improvements or additions to documentation module:core module:quantization
#2162 opened Aug 1, 2025 by Potabk Loading…
13
[main][Bugfix] Fix unable to load qwen3_moe quantized weights module:tests
#2161 opened Aug 1, 2025 by zhoux77899 Loading…
3
attn tp module:core module:ops
#2159 opened Aug 1, 2025 by momo609 Loading…
add super kernel for decode moe module:core module:ops module:quantization
#2157 opened Aug 1, 2025 by NNUCJ Loading…
3
[Fix] Adjust use_aclgraph logic module:ops
#2156 opened Aug 1, 2025 by yiz-liu Loading…
4
Remove cat ci/build documentation Improvements or additions to documentation module:core module:ops module:quantization module:tests module:tools
#2153 opened Jul 31, 2025 by loukong33 Loading…
1
ut: add example and e2e test for sleepmode in external_launcher module:tests
#2152 opened Jul 31, 2025 by loukong33 Loading…
6
refactor fused_moe.py merge-conflicts module:ops module:quantization
#2150 opened Jul 31, 2025 by shiyuan680 Loading…
3
ProTip! Filter pull requests by the default branch with base:main.