This website requires JavaScript.
Explore
Help
Sign In
karylab_agents
/
vllm
Watch
1
Star
0
Fork
0
forked from
Karylab-cklius/vllm
Code
Pull Requests
2
Actions
1
Packages
Activity
Files
1b2570ec7749e48b9c7a4e32ca055d1bd2fd2ea5
vllm
/
csrc
/
libtorch_stable
/
quantization
/
fp4
T
History
Jakub Zakrzewski
and
GitHub
6fbec8ed47
[Bugfix][Kernel] nvfp4 cutlass MoE: fix nvfp4 experts quant out-of-bounds read for expert counts not divisible by 4 or 16 (
#40351
)
...
Signed-off-by: Jakub Zakrzewski <
jzakrzewski@nvidia.com
>
2026-04-21 19:06:09 +00:00
..
activation_nvfp4_quant_fusion_kernels.cu
…
mxfp4_blockwise_moe_kernel.cu
[Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (
#37463
)
2026-04-17 16:42:32 -07:00
mxfp4_experts_quant.cu
[Bugfix] Guard mxfp4_experts_quant bindings on ENABLE_NVFP4_SM100 (
#40191
)
2026-04-18 13:58:46 -07:00
nvfp4_blockwise_moe_kernel.cu
…
nvfp4_experts_quant.cu
[Bugfix][Kernel] nvfp4 cutlass MoE: fix nvfp4 experts quant out-of-bounds read for expert counts not divisible by 4 or 16 (
#40351
)
2026-04-21 19:06:09 +00:00
nvfp4_quant_entry.cu
[Compile] Fix nvfp4 compile warning (
#38573
)
2026-04-01 18:28:57 +00:00
nvfp4_quant_kernels.cu
…
nvfp4_scaled_mm_entry.cu
…
nvfp4_scaled_mm_kernels.cu
…
nvfp4_scaled_mm_sm120_kernels.cu
…
nvfp4_utils.cuh
…