mirror of https://github.com/vllm-project/vllm
24 lines
389 B
Plaintext
24 lines
389 B
Plaintext
# testing
|
|
pytest
|
|
tensorizer>=2.9.0
|
|
pytest-forked
|
|
pytest-asyncio
|
|
pytest-rerunfailures
|
|
pytest-shard
|
|
|
|
# testing utils
|
|
awscli
|
|
einops # required for MPT
|
|
httpx
|
|
peft
|
|
requests
|
|
ray
|
|
sentence-transformers # required for embedding
|
|
sparseml==1.8.0 # required for compressed-tensors
|
|
compressed-tensors==0.4.0 # required for compressed-tensors
|
|
|
|
# Benchmarking
|
|
aiohttp
|
|
|
|
# quantization
|
|
bitsandbytes==0.42.0 |