diff --git a/requirements/cuda.txt b/requirements/cuda.txt index 1e0a945e5a7..99a45c9d3ca 100644 --- a/requirements/cuda.txt +++ b/requirements/cuda.txt @@ -21,7 +21,7 @@ nvidia-cudnn-frontend>=1.13.0,<1.19.0 fastsafetensors >= 0.2.2 # QuACK and Cutlass DSL for FA4 (cute-DSL implementation) -nvidia-cutlass-dsl[cu13]==4.5.0 +nvidia-cutlass-dsl[cu13]==4.5.2 quack-kernels>=0.3.3 # Tokenspeed_MLA for faster mla with spec decode