diff --git a/requirements/cuda.txt b/requirements/cuda.txt index abff2525af9..0be8fa2f0d6 100644 --- a/requirements/cuda.txt +++ b/requirements/cuda.txt @@ -20,6 +20,6 @@ nvidia-cudnn-frontend>=1.13.0,<1.19.0 # Required for faster safetensors model loading fastsafetensors >= 0.2.2 -# QuACK and Cutlass DSL for FA4 (cute-DSL implementation) -nvidia-cutlass-dsl>=4.4.2 +# For dequantize_and_gather_k_cache_cutedsl +nvidia-cutlass-dsl>=4.5.0 quack-kernels>=0.3.3