mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-09 23:15:31 +08:00
a9f55dc588
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com> Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
18 lines
892 B
Plaintext
18 lines
892 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
|
|
# 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==0.4.1
|
|
# Triton Kernels are needed for mxfp4 fused moe. (Should be updated alongside torch)
|
|
triton_kernels @ git+https://github.com/triton-lang/triton.git@v3.5.0#subdirectory=python/triton_kernels
|