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

[Kernel] Add non-gated support for NVFP4 CUTLASS MoE (#37320)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2026-03-17 23:12:04 +01:00
committed by GitHub
parent 3ed7b1e6e0
commit 09e4576f65
8 changed files with 53 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
csrc/torch_bindings.cpp
View File

@@ -489,8 +489,8 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
" Tensor! problem_sizes1, Tensor! problem_sizes2, "
" Tensor! input_permutation, "
" Tensor! output_permutation, int num_experts, "
" int n, int k, Tensor? blockscale_offsets) -> "
"()");
" int n, int k, Tensor? blockscale_offsets, "
" bool is_gated) -> ()");
ops.impl("get_cutlass_moe_mm_data", torch::kCUDA, &get_cutlass_moe_mm_data);
// compute per-expert problem sizes from expert_first_token_offset