21 lines
698 B
Plaintext
21 lines
698 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
|
|
torch==2.10.0
|
|
torchaudio==2.10.0
|
|
# These must be updated alongside torch
|
|
torchvision==0.25.0 # 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==0.6.4
|
|
# 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
|