karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 2 Packages Activity
Files
fix/deepseek-v4-nvidia-mhc-warmup
vllm/csrc/quickreduce
T
History
haoyangli0109GitHubtjtanaamergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Douglas LehrAndreas Karatzas
 7f599d7854 [communication] [bugfix] fix quickreduce acc error in cudagraph mode (#46913) 
Signed-off-by: Haoyang Li <lihaoyang0109@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-27 01:38:45 -07:00
..
base.h
[ROCM] [Communication] Add INT3 quantization method for quickreduce (#45666)
2026-06-25 15:14:15 +00:00
quick_reduce_impl.cuh
[ROCM] [Communication] Add INT3 quantization method for quickreduce (#45666)
2026-06-25 15:14:15 +00:00
quick_reduce.h
[communication] [bugfix] fix quickreduce acc error in cudagraph mode (#46913)
2026-07-27 01:38:45 -07:00