- 04 Jun, 2024 4 commits
-
-
afeldman-nm authored
[Bugfix]: During testing, use pytest monkeypatch for safely overriding the env var that indicates the vLLM backend (#5210)
-
Woosuk Kwon authored
-
Zhuohan Li authored
-
Toshiki Kataoka authored
-
- 03 Jun, 2024 7 commits
-
-
Breno Faria authored
-
Kevin H. Luu authored
Signed-off-by:kevin <kevin@anyscale.com>
-
Kaiyang Chen authored
-
Yuan authored
-
Tyler Michael Smith authored
-
Antoni Baum authored
-
Cyrus Leung authored
-
- 02 Jun, 2024 4 commits
-
-
Cyrus Leung authored
-
Divakar Verma authored
This PR enables the fused topk_softmax kernel used in moe layer for HIP
-
Avinash Raj authored
-
Simon Mo authored
-
- 01 Jun, 2024 11 commits
-
-
Robert Shaw authored
Co-authored-by:mgoin <michael@neuralmagic.com>
-
Daniil Arapov authored
-
Zhuohan Li authored
-
chenqianfzh authored
-
Nadav Shmayovits authored
-
Ye Cao authored
Signed-off-by:Ye Cao <caoye.cao@alibaba-inc.com>
-
Varun Sundar Rabindranath authored
Co-authored-by:
Varun Sundar Rabindranath <varun@neuralmagic.com> Co-authored-by:
Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
-
Tyler Michael Smith authored
-
Daniele authored
-
Tyler Michael Smith authored
-
Nick Hill authored
-
- 31 May, 2024 7 commits
-
-
Cody Yu authored
-
functionxu123 authored
Co-authored-by:xuhao <xuhao@cambricon.com>
-
Simon Mo authored
Revert "[Kernel] Marlin_24: Ensure the mma.sp instruction is using the ::ordered_metadata modifier (introduced with PTX 8.5)" (#5149)
-
SnowDist authored
Co-authored-by:Zhuohan Li <zhuohan123@gmail.com>
-
simon-mo authored
-
Alexander Matveev authored
[Kernel] Marlin_24: Ensure the mma.sp instruction is using the ::ordered_metadata modifier (introduced with PTX 8.5) (#5136)
-
Robert Shaw authored
-
- 30 May, 2024 7 commits
-
-
Simon Mo authored
-
Simon Mo authored
-
Chansung Park authored
Co-authored-by:Roger Wang <ywang@roblox.com>
-
Cyrus Leung authored
-
Hyunsung Lee authored
-
youkaichao authored
-
Robert Shaw authored
-
