mirror of https://github.com/vllm-project/vllm
13 lines
318 B
Plaintext
13 lines
318 B
Plaintext
ninja # For faster builds.
|
|
psutil
|
|
ray >= 2.5.1
|
|
sentencepiece # Required for LLaMA tokenizer.
|
|
numpy
|
|
torch == 2.1.2
|
|
transformers >= 4.36.0 # Required for Mixtral.
|
|
xformers == 0.0.23.post1 # Required for CUDA 12.1.
|
|
fastapi
|
|
uvicorn[standard]
|
|
pydantic == 1.10.13 # Required for OpenAI server.
|
|
aioprometheus[starlette]
|