biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Feat] Support non-gated MoE with Marlin, NVFP4 CUTLASS, FP8, INT8, compressed-tensors (#32257)

Browse Source 
Signed-off-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@ipp1-1429.ipp1a1.colossus.nvidia.com>
This commit is contained in:
TomerBN-Nvidia
2026-01-16 02:15:05 +02:00
committed by GitHub
parent aca5c51487
commit c277fbdf31
17 changed files with 226 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/envs.py
View File

@@ -1451,6 +1451,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
# - "flashinfer-cudnn": use flashinfer cudnn GEMM backend
# - "flashinfer-trtllm": use flashinfer trtllm GEMM backend
# - "flashinfer-cutlass": use flashinfer cutlass GEMM backend
# - "marlin": use marlin GEMM backend (for GPUs without native FP4 support)
# - <none>: automatically pick an available backend
"VLLM_NVFP4_GEMM_BACKEND": env_with_choices(
"VLLM_NVFP4_GEMM_BACKEND",
@@ -1460,6 +1461,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
"flashinfer-trtllm",
"flashinfer-cutlass",
"cutlass",
"marlin",
],
),
# Controls garbage collection during CUDA graph capture.