mirror of
https://github.com/vllm-project/vllm.git
synced 2026-06-06 00:16:14 +00:00
Michael Goin
32 lines
959 B
Plaintext
32 lines
959 B
Plaintext
# Common dependencies
|
|
-r common.txt
|
|
|
|
numba == 0.65.0 # Required for N-gram speculative decoding
|
|
|
|
# Dependencies for NVIDIA GPUs
|
|
torch==2.11.0
|
|
torchaudio==2.11.0
|
|
# These must be updated alongside torch
|
|
torchvision==0.26.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
|
|
# FlashInfer should be updated together with the Dockerfile
|
|
flashinfer-python==0.6.12
|
|
flashinfer-cubin==0.6.12
|
|
apache-tvm-ffi==0.1.9
|
|
tilelang==0.1.9
|
|
# 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
|
|
|
|
# Required for faster safetensors model loading
|
|
fastsafetensors >= 0.3.2
|
|
|
|
# QuACK and Cutlass DSL for FA4 (cute-DSL implementation)
|
|
nvidia-cutlass-dsl[cu13]==4.5.2
|
|
quack-kernels>=0.3.3
|
|
|
|
# Tokenspeed_MLA for faster mla with spec decode
|
|
tokenspeed-mla==0.1.2
|
|
|
|
# Humming kernels for quantization gemm
|
|
humming-kernels[cu13]==0.1.4
|