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
68ee8300a047db78fb52bac477daaaac7be11216
vLLM
/
vllm
/
model_executor
/
kernels
/
linear
/
nvfp4
T
History
Mohammad Miadh Angkad
d1a38c2762
[Kernel][Performance] Add FlashInfer cutedsl NVFP4 GEMM backend (
#42235
)
...
Signed-off-by: Mohammad Miadh Angkad <
176301910+mmangkad@users.noreply.github.com
>
2026-06-22 16:17:18 -04:00
..
__init__.py
…
base.py
Add the QuantizedActivation linear-kernel contract (
#44260
)
2026-06-12 13:48:15 -07:00
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
…
fbgemm.py
…
flashinfer.py
[Kernel][Performance] Add FlashInfer cutedsl NVFP4 GEMM backend (
#42235
)
2026-06-22 16:17:18 -04:00
marlin.py
…