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

[MoE Refactor][3/N] Deprecate cutlass block quant fp8 (b200) (#30990)

Browse Source 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
This commit is contained in:
Robert Shaw
2025-12-19 16:09:54 -05:00
committed by GitHub
parent 5f6477d1d0
commit 83a317f650
8 changed files with 3 additions and 704 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
csrc/torch_bindings.cpp
View File

@@ -416,13 +416,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
" Tensor alpha) -> ()");
ops.impl("cutlass_scaled_fp4_mm", torch::kCUDA, &cutlass_scaled_fp4_mm);
// cutlass blockwise scaledgroup GEMM
ops.def(
"cutlass_blockwise_scaled_grouped_mm(Tensor! output, Tensor a, Tensor b, "
"Tensor scales_a, Tensor scales_b, "
"Tensor problem_sizes, Tensor expert_offsets) -> ()");
// conditionally compiled so impl registration is in source file
// cutlass nvfp4 block scaled group GEMM
ops.def(
"cutlass_fp4_group_mm(Tensor! out, Tensor a, Tensor b,"