Skip to content

[Fix] Revert back to using CUTLASS mm_fp4 backend #17369

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Fridge003 merged 2 commits into from
Jan 31, 2026
Merged

[Fix] Revert back to using CUTLASS mm_fp4 backend #17369

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
152dff0
more
b8zhong Jan 19, 2026
5ead9ea
Merge branch 'main' into brayden/tiny-fix-flashinfer-mmfp4
b8zhong Jan 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion python/sglang/srt/layers/quantization/modelopt_quant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,7 +131,11 @@ def fp4_gemm(
fp4_backend = get_fp4_gemm_runner_backend()
if enable_flashinfer_fp4_gemm:
# Use the remapping logic to convert SGLang backend names to FlashInfer API names
backend = fp4_backend.get_flashinfer_backend()
backend = (
fp4_backend.get_flashinfer_backend()
if not fp4_backend.is_auto()
else "cutlass"
Comment thread
b8zhong marked this conversation as resolved.
)
return flashinfer_fp4_gemm(
input, weight, input_sf, weight_sf, alpha, out_dtype, backend=backend
)
Expand Down
Loading