Skip to content

Actions: ROCm/vllm

Cleanup PR Body

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
96 workflow runs
96 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Revert "[OPT] improve rms_norm kernel"
Cleanup PR Body #21: Pull request #293 opened by gshtras
November 26, 2024 23:37 16s
November 26, 2024 23:37 16s
devdocker README from https://github.com/powderluv/vllm-docs
Cleanup PR Body #20: Pull request #292 opened by gshtras
November 25, 2024 20:14 17s
November 25, 2024 20:14 17s
Base docker image
Cleanup PR Body #19: Pull request #290 opened by gshtras
November 22, 2024 18:37 26s
November 22, 2024 18:37 26s
Added --output-json parameter in the P3l script. Using arg_utils to support all vllm args
Cleanup PR Body #18: Pull request #289 opened by gshtras
November 22, 2024 18:24 24s
November 22, 2024 18:24 24s
enable softcap and gemma2
Cleanup PR Body #17: Pull request #288 opened by hliuca
November 20, 2024 21:57 20s
November 20, 2024 21:57 20s
Disable custom all-reduce on two Navi GPUs
Cleanup PR Body #16: Pull request #287 opened by hyoon1
November 19, 2024 19:38 30s
November 19, 2024 19:38 30s
Upstream merge 24 11 18
Cleanup PR Body #15: Pull request #286 opened by gshtras
November 19, 2024 15:59 21s
November 19, 2024 15:59 21s
Enable CK Attention for Navi31
Cleanup PR Body #14: Pull request #285 opened by hyoon1
November 18, 2024 23:27 20s
November 18, 2024 23:27 20s
Cuda compile fix2
Cleanup PR Body #13: Pull request #284 opened by hliuca
November 17, 2024 01:48 18s
November 17, 2024 01:48 18s
Gradlib torch extension cmake
Cleanup PR Body #12: Pull request #282 opened by gshtras
November 15, 2024 19:38 20s
November 15, 2024 19:38 20s
use CK FA for glm-4v on navi3
Cleanup PR Body #11: Pull request #281 opened by jfactory07
November 15, 2024 05:36 19s
November 15, 2024 05:36 19s
CUDA compilation fix
Cleanup PR Body #10: Pull request #278 edited by gshtras
November 14, 2024 16:38 25s
November 14, 2024 16:38 25s
Improve the heuristic logic for fp8 weight padding
Cleanup PR Body #9: Pull request #279 edited by charlifu
November 14, 2024 16:20 15s
November 14, 2024 16:20 15s
Improve the heuristic logic for fp8 weight padding
Cleanup PR Body #8: Pull request #279 opened by charlifu
November 14, 2024 16:18 16s
November 14, 2024 16:18 16s
mixtral8x22B moe configs mi300 TP=1,2,4,8
Cleanup PR Body #7: Pull request #277 opened by divakar-amd
November 14, 2024 03:33 18s
November 14, 2024 03:33 18s
Fix kernel cache miss and add RDNA configs
Cleanup PR Body #6: Pull request #246 edited by hyoon1
November 13, 2024 19:19 33s
November 13, 2024 19:19 33s
Add vectorized rms_norm support for Navi31
Cleanup PR Body #5: Pull request #273 edited by gshtras
November 13, 2024 18:12 23s
November 13, 2024 18:12 23s
Running linter actions on develop branch
Cleanup PR Body #4: Pull request #275 opened by gshtras
November 13, 2024 17:09 22s
November 13, 2024 17:09 22s
rocm support for moe tuning script
Cleanup PR Body #3: Pull request #251 edited by divakar-amd
November 13, 2024 14:16 28s
November 13, 2024 14:16 28s
[BUGFIX] Llama3.2 fa crash fix
Cleanup PR Body #2: Pull request #274 edited by maleksan85
November 12, 2024 23:30 17s
November 12, 2024 23:30 17s
[OPT] improve rms_norm kernel
Cleanup PR Body #1: Pull request #258 edited by gshtras
November 12, 2024 16:47 24s
November 12, 2024 16:47 24s