cuda.txt

# Common dependencies
-r common.txt

numba == 0.61.2 # Required for N-gram speculative decoding

# Dependencies for NVIDIA GPUs
# FlashInfer should be updated together with the Dockerfile
flashinfer-python==0.6.6
# Cap nvidia-cudnn-frontend (transitive dep of flashinfer) due to
# breaking changes in 1.19.0
nvidia-cudnn-frontend>=1.13.0,<1.19.0

# QuACK and Cutlass DSL for FA4 (cute-DSL implementation)
nvidia-cutlass-dsl>=4.4.0.dev1
quack-kernels>=0.2.7