diff --git a/cutedsl/bridge.py b/cutedsl/bridge.py index dfbdd521..4d9ba7a0 100644 --- a/cutedsl/bridge.py +++ b/cutedsl/bridge.py @@ -344,6 +344,5 @@ def run_nvfp4_grouped_gemm( stream, global_scale_a=gsa_c, global_scale_b=gsb_c, ) - torch.cuda.synchronize() return out