cuda.txt

# Common dependencies
-r common.txt

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

# Dependencies for NVIDIA GPUs
ray[cgraph]>=2.48.0 # Ray Compiled Graph, required for pipeline parallelism in V1.
torch==2.8.0
torchaudio==2.8.0
# These must be updated alongside torch
torchvision==0.23.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
# https://github.com/facebookresearch/xformers/releases/tag/v0.0.32.post1
xformers==0.0.32.post1; platform_system == 'Linux' and platform_machine == 'x86_64'  # Requires PyTorch >= 2.8
# FlashInfer should be updated together with the Dockerfile
flashinfer-python==0.4.0