Skip to content

Actions: vllm-project/vllm-ascend

Actions

image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
image.yml
130 workflow runs
130 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Ray Worker Ops Optimization (#136) image #130: Commit 202b39a pushed by wangxiyuan
February 21, 2025 14:45 34m 21s main
main
February 21, 2025 14:45 34m 21s
[Model Runner][Performance] Cache the jugement result of is_encoder_d… image #129: Commit 386817b pushed by wangxiyuan
February 21, 2025 14:43 36m 21s main
main
February 21, 2025 14:43 36m 21s
[BugFix] add int8 cache dtype && modify initialization of attention image #128: Pull request #134 synchronize by Angazenn
February 21, 2025 13:26 27m 47s Angazenn:develop
Angazenn:develop
February 21, 2025 13:26 27m 47s
[Model Runner][Performance] Cache the jugement result of is_encoder_decoder to decrease framework overhead image #127: Pull request #138 opened by whx-sjtu
February 21, 2025 12:38 29m 57s whx-sjtu:is_enc_doc_opt
whx-sjtu:is_enc_doc_opt
February 21, 2025 12:38 29m 57s
[BugFix]add int8 cache dtype when using attention quantization image #126: Pull request #128 synchronize by Angazenn
February 21, 2025 10:47 32m 9s Angazenn:bug_fix
Angazenn:bug_fix
February 21, 2025 10:47 32m 9s
modify:Eliminate redundant operations in the code to improve performance image #125: Pull request #137 opened by Yaphets24
February 21, 2025 10:22 31m 44s Yaphets24:main
Yaphets24:main
February 21, 2025 10:22 31m 44s
Ray Worker Ops Optimization image #124: Pull request #136 synchronize by noemotiovon
February 21, 2025 09:50 31m 19s noemotiovon:ray_ops_optimization
noemotiovon:ray_ops_optimization
February 21, 2025 09:50 31m 19s
Ray Worker Ops Optimization image #123: Pull request #136 synchronize by noemotiovon
February 21, 2025 09:43 32m 47s noemotiovon:ray_ops_optimization
noemotiovon:ray_ops_optimization
February 21, 2025 09:43 32m 47s
Ray Worker Ops Optimization image #122: Pull request #136 opened by noemotiovon
February 21, 2025 09:41 34m 35s noemotiovon:ray_ops_optimization
noemotiovon:ray_ops_optimization
February 21, 2025 09:41 34m 35s
[BugFix] add int8 cache dtype && modify initialization of attention image #121: Pull request #134 opened by Angazenn
February 21, 2025 09:14 27m 33s Angazenn:develop
Angazenn:develop
February 21, 2025 09:14 27m 33s
[Platform] add dispatch key (#17) image #120: Commit dd425d6 pushed by wangxiyuan
February 21, 2025 09:10 39m 25s main
main
February 21, 2025 09:10 39m 25s
[Core] Cherry pick from 0.7.1 to keep the main code newest (#127) image #119: Commit 5f46501 pushed by wangxiyuan
February 21, 2025 09:07 39m 47s main
main
February 21, 2025 09:07 39m 47s
[Core] Cherry pick from 0.7.1 to keep the main code newest image #118: Pull request #127 synchronize by wangxiyuan
February 21, 2025 08:47 31m 28s wangxiyuan:cherry-pick-main
wangxiyuan:cherry-pick-main
February 21, 2025 08:47 31m 28s
[WIP][Feature] Implement native fused MoE layer image #117: Pull request #121 synchronize by yiz-liu
February 21, 2025 08:33 34m 50s yiz-liu:main
yiz-liu:main
February 21, 2025 08:33 34m 50s
[Core] Cherry pick from 0.7.1 to keep the main code newest image #116: Pull request #127 synchronize by wangxiyuan
February 21, 2025 08:18 33m 24s wangxiyuan:cherry-pick-main
wangxiyuan:cherry-pick-main
February 21, 2025 08:18 33m 24s
[BugFix]add int8 cache dtype when using attention quantization image #115: Pull request #128 synchronize by Angazenn
February 21, 2025 02:52 31m 55s Angazenn:bug_fix
Angazenn:bug_fix
February 21, 2025 02:52 31m 55s
[Core] Cherry pick from 0.7.1 to keep the main code newest image #114: Pull request #127 synchronize by wangxiyuan
February 21, 2025 02:44 35m 54s wangxiyuan:cherry-pick-main
wangxiyuan:cherry-pick-main
February 21, 2025 02:44 35m 54s
[BugFix]add int8 cache dtype when using attention quantization image #113: Pull request #128 synchronize by Angazenn
February 21, 2025 02:20 42m 5s Angazenn:bug_fix
Angazenn:bug_fix
February 21, 2025 02:20 42m 5s
[BugFix]add int8 cache dtype when using attention quantization image #112: Pull request #128 opened by Angazenn
February 21, 2025 02:11 36m 16s Angazenn:bug_fix
Angazenn:bug_fix
February 21, 2025 02:11 36m 16s
[Core] Cherry pick from 0.7.1 to keep the main code newest image #111: Pull request #127 opened by wangxiyuan
February 21, 2025 02:01 34m 57s wangxiyuan:cherry-pick-main
wangxiyuan:cherry-pick-main
February 21, 2025 02:01 34m 57s
[Core] Add Ascend Quant Config to main branch image #110: Pull request #33 synchronize by Angazenn
February 21, 2025 01:59 38m 48s Angazenn:main
Angazenn:main
February 21, 2025 01:59 38m 48s
[BugFix]Add int8 cache dtype when using ascend attention quantization image #109: Pull request #125 synchronize by Angazenn
February 21, 2025 01:47 27m 44s Angazenn:develop
Angazenn:develop
February 21, 2025 01:47 27m 44s
[BugFix]Add int8 cache dtype when using ascend attention quantization image #108: Pull request #125 opened by Angazenn
February 21, 2025 01:44 30m 29s Angazenn:develop
Angazenn:develop
February 21, 2025 01:44 30m 29s
feat:modify rope forward image #107: Pull request #114 synchronize by Yaphets24
February 20, 2025 10:18 31m 30s Yaphets24:v0.7.1-dev
Yaphets24:v0.7.1-dev
February 20, 2025 10:18 31m 30s
[WIP][Feature] Implement native fused MoE layer image #106: Pull request #121 opened by yiz-liu
February 20, 2025 09:26 35m 21s yiz-liu:main
yiz-liu:main
February 20, 2025 09:26 35m 21s