diff --git a/requirements/cuda.txt b/requirements/cuda.txt index 1f5a9642b2..5e193bac5a 100644 --- a/requirements/cuda.txt +++ b/requirements/cuda.txt @@ -25,7 +25,7 @@ nvidia-cutlass-dsl[cu13]==4.8.0 quack-kernels==0.6.5 # Required by MSA # Tokenspeed_MLA for faster mla with spec decode -tokenspeed-mla==0.2.15; platform_system == "Linux" +tokenspeed-mla==2.0.2; platform_system == "Linux" # Humming kernels for quantization gemm humming-kernels[cu13]==0.1.16