vllm/requirements-common.txt

psutil
sentencepiece  # Required for LLaMA tokenizer.
numpy < 2.0.0
requests
tqdm
py-cpuinfo
transformers >= 4.43.2  # Required for Chameleon and Llama 3.1 hotfox.
tokenizers >= 0.19.1  # Required for Llama 3.
protobuf # Required by LlamaTokenizer.
fastapi
aiohttp
openai >= 1.40.0 # Ensure modern openai package (ensure types module present)
uvicorn[standard]
pydantic >= 2.8  # Required for OpenAI server.
pillow  # Required for image processing
prometheus_client >= 0.18.0
prometheus-fastapi-instrumentator >= 7.0.0
tiktoken >= 0.6.0  # Required for DBRX tokenizer
lm-format-enforcer == 0.10.6
outlines >= 0.0.43, < 0.1 # Requires torch >= 2.1.0
typing_extensions >= 4.10
filelock >= 3.10.4 # filelock starts to support `mode` argument from 3.10.4
partial-json-parser # used for parsing partial JSON outputs
pyzmq
msgspec
gguf == 0.9.1
importlib_metadata
mistral_common >= 1.4.0
pyyaml
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
einops # Required for Qwen2-VL.