Skip to content

Actions: vllm-project/vllm-ascend

Actions

ascend test / accuracy

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
accuracy_test.yaml
121 workflow run results
121 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Build] Move numba/quart to requirments and update DS baseline and sync graph typo fix ascend test / accuracy #125: Pull request #1121 labeled by Yikun
Skipped Yikun:fix-numba
Yikun:fix-numba
Skipped
[Build] Move numba/quart to requirments and update DS baseline and sync graph typo fix ascend test / accuracy #124: Pull request #1121 labeled by Yikun
1s Yikun:fix-numba
Yikun:fix-numba
1s
[Build] Move numba/quart to requirments and update DS baseline and sync graph typo fix ascend test / accuracy #123: Pull request #1121 labeled by Yikun
Skipped Yikun:fix-numba
Yikun:fix-numba
Skipped
[Build] Move numba/quart to requirments and update DS baseline and sync graph typo fix ascend test / accuracy #122: Pull request #1121 labeled by Yikun
1s Yikun:fix-numba
Yikun:fix-numba
1s
[CherryPick] Add unpadded Qwen2.5-VL for verl scenario ascend test / accuracy #120: Pull request #1095 labeled by wangxiyuan
1s wangxiyuan:cherry-pick-073
wangxiyuan:cherry-pick-073
1s
[SpecDecode][CI] Set default values to fix spec decode and fix multicard CI ascend test / accuracy #119: Pull request #1109 labeled by Yikun
1s Yikun:pr/1105
Yikun:pr/1105
1s
[SpecDecode][CI] Set default values to fix spec decode and fix multicard CI ascend test / accuracy #118: Pull request #1109 labeled by Yikun
Skipped Yikun:pr/1105
Yikun:pr/1105
Skipped
[perf] optimize apply_penalties & topKtopP for V0&V1 Engine ascend test / accuracy #117: Pull request #1107 labeled by wangxiyuan
1s linfeng-yuan:sampler_optimization
linfeng-yuan:sampler_optimization
1s
[Doc] Add 0.9.0rc1 release note ascend test / accuracy #116: Pull request #1106 labeled by wangxiyuan
1s wangxiyuan:add_090_release
wangxiyuan:add_090_release
1s
[Fix] Set default values to fix spec decode ascend test / accuracy #114: Pull request #1105 labeled by MengqingCao
1s yiz-liu:fix-spec-decode
yiz-liu:fix-spec-decode
1s
[Fix] Set default values to fix spec decode ascend test / accuracy #113: Pull request #1105 labeled by MengqingCao
2s yiz-liu:fix-spec-decode
yiz-liu:fix-spec-decode
2s
[perf]: support dual-batch overlap(dbo) for deepseek ascend test / accuracy #112: Pull request #941 labeled by wangxiyuan
1s zxdukki:dev_multistream_overlap
zxdukki:dev_multistream_overlap
1s
[BugFix] Fix data parallel ascend test / accuracy #111: Pull request #940 labeled by wangxiyuan
1s yiz-liu:fix-dp
yiz-liu:fix-dp
1s
Add qwen2.5 vl multimodal feature for vllm-ascend v1 ascend test / accuracy #110: Pull request #736 labeled by wangxiyuan
36m 22s ChenTaoyu-SJTU:add_qwen2.5_vl_multimodal
ChenTaoyu-SJTU:add_qwen2.5_vl_multimodal
36m 22s
[Fix] Set default values to fix spec decode ascend test / accuracy #109: Pull request #1105 labeled by wangxiyuan
1s yiz-liu:fix-spec-decode
yiz-liu:fix-spec-decode
1s
feat: support compile multiple batch graph ascend test / accuracy #108: Pull request #1085 labeled by ApsarasX
1s NeverRaR:github/dev/cache_compile
NeverRaR:github/dev/cache_compile
1s
[Worker][V1] Support sleep mode for v1 ascend test / accuracy #107: Pull request #1084 labeled by wangxiyuan
1s Potabk:sleep_mode_v1
Potabk:sleep_mode_v1
1s
Avoid unfused Transpose in DeepSeekV3 EP256 MoE layer ascend test / accuracy #106: Pull request #1091 labeled by wangxiyuan
1s sdmyzlp:br_infer_opt_0
sdmyzlp:br_infer_opt_0
1s
[CI]Moe alltoall communication optimization ascend test / accuracy #105: Pull request #1067 labeled by wangxiyuan
1s weijinqian0:moe_alltoall_v6
weijinqian0:moe_alltoall_v6
1s
[Misc] Adjust the default profiler configuration ascend test / accuracy #104: Pull request #1097 labeled by ApsarasX
1s ApsarasX:community-profiler
ApsarasX:community-profiler
1s
[Bugfix][DP] Add with_prefill_across_dp to AscendMetadata to fix dp ascend test / accuracy #103: Pull request #1094 labeled by wangxiyuan
Skipped MengqingCao:fixdp
MengqingCao:fixdp
Skipped
[ModelRunner] Support embedding inputs ascend test / accuracy #102: Pull request #916 labeled by wangxiyuan
Skipped Potabk:dev
Potabk:dev
Skipped
[Kernel] Remove cumsum in groupedmatmul ascend test / accuracy #101: Pull request #987 labeled by wangxiyuan
1s hahazhky:main
hahazhky:main
1s
[ModelRunner]Add profile execute duration observation ascend test / accuracy #100: Pull request #1013 labeled by Yikun
1s depeng1994:main
depeng1994:main
1s
Try pass accuracy test for qwen2.5vl in vllm-ascend v1 ascend test / accuracy #98: Pull request #1082 labeled by ChenTaoyu-SJTU
6h 52m 52s ChenTaoyu-SJTU:try_pass_accuracy_test_for_qwen2.5vl_in_vllm_ascend_v1
ChenTaoyu-SJTU:try_pass_accuracy_test_for_qwen2.5vl_in_vllm_ascend_v1
6h 52m 52s