- 11 Jun, 2024 18 commits
-
-
youkaichao authored
-
Nick Hill authored
Co-authored-by:Antoni Baum <antoni.baum@protonmail.com>
-
youkaichao authored
-
sasha0552 authored
-
Ali Panahi authored
-
Junichi Sato authored
-
Cade Daniel authored
-
Kuntai Du authored
Co-authored-by:simon-mo <simon.mo@hey.com>
-
Cade Daniel authored
-
SangBin Cho authored
Co-authored-by:
DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by:
ywang96 <ywang@roblox.com>
-
Woosuk Kwon authored
-
Roger Wang authored
-
youkaichao authored
-
Cyrus Leung authored
-
maor-ps authored
Co-authored-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Nick Hill authored
-
Kevin H. Luu authored
Signed-off-by:kevin <kevin@anyscale.com>
-
Michael Goin authored
-
- 10 Jun, 2024 12 commits
-
-
Simon Mo authored
-
Woosuk Kwon authored
-
Roger Wang authored
-
Kevin H. Luu authored
Signed-off-by:kevin <kevin@anyscale.com>
-
Kevin H. Luu authored
Signed-off-by:kevin <kevin@anyscale.com>
-
Cyrus Leung authored
-
Itay Etelis authored
-
Cyrus Leung authored
Co-authored-by:Roger Wang <ywang@roblox.com>
-
Cyrus Leung authored
-
youkaichao authored
-
Roger Wang authored
-
Dipika Sikka authored
Co-authored-by:Michael Goin <michael@neuralmagic.com>
-
- 09 Jun, 2024 4 commits
-
-
Bla_ckB authored
-
bnellnm authored
-
youkaichao authored
[mis][ci/test] fix flaky test in tests/test_sharded_state_loader.py (#5361)
-
youkaichao authored
[Core][CUDA Graph] add output buffer for cudagraph to reduce memory footprint (#5074)
-
- 08 Jun, 2024 6 commits
-
-
Michael Goin authored
-
youkaichao authored
[CI/Test] improve robustness of test by replacing del with context manager (vllm_runner) (#5357)
-
youkaichao authored
[CI/Test] improve robustness of test by replacing del with context manager (hf_runner) (#5347)
-
Hongxia Yang authored
-
Benjamin Kitor authored
-
Cheng Li authored
Bug description: With torch 2.4.0.dev20240603+cu121, cutlass_fp8_supported outputs False, and the (capability, version) before the comparison is (90, 11111111112) This PR fixes the support check for FP8 CUTLASS ( cutlass_fp8_supported) which was introduced in https://github.com/vllm-project/vllm/pull/5183.
-