vllm/requirements/cuda.txt
2025-10-30 10:22:30 -07:00

16 lines
724 B
Plaintext

# 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==2.9.0
torchaudio==2.9.0
# These must be updated alongside torch
torchvision==0.24.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
# Build from https://github.com/facebookresearch/xformers/releases/tag/v0.0.32.post1
xformers==0.0.33+5d4b92a5.d20251029; platform_system == 'Linux' and platform_machine == 'x86_64' # Requires PyTorch >= 2.9
# FlashInfer should be updated together with the Dockerfile
flashinfer-python==0.4.1