This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
ded871201a424dd0d28a00aaf74c5786457a18ee
vLLM
/
vllm
/
model_executor
/
kernels
/
linear
/
nvfp4
T
History
Wentao Ye
37ece593c1
[Perf] Padded nvfp4 quant kernel to remove additional copy, 2.4%~5.7% e2e performance improvement (
#42774
)
...
Signed-off-by: yewentao256 <
zhyanwentao@126.com
>
2026-05-18 16:38:12 -07:00
..
__init__.py
[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (
#39129
)
2026-04-09 15:05:36 -04:00
base.py
[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (
#39129
)
2026-04-09 15:05:36 -04:00
cutlass.py
[Perf] Padded nvfp4 quant kernel to remove additional copy, 2.4%~5.7% e2e performance improvement (
#42774
)
2026-05-18 16:38:12 -07:00
emulation.py
[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (
#39129
)
2026-04-09 15:05:36 -04:00
fbgemm.py
[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (
#39129
)
2026-04-09 15:05:36 -04:00
flashinfer.py
[Perf] Padded nvfp4 quant kernel to remove additional copy, 2.4%~5.7% e2e performance improvement (
#42774
)
2026-05-18 16:38:12 -07:00
marlin.py
[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (
#39129
)
2026-04-09 15:05:36 -04:00
