vllm/requirements/common.txt

regex # Replace re for higher-performance regex matching
cachetools
psutil
sentencepiece  # Required for LLaMA tokenizer.
numpy
requests >= 2.26.0
tqdm
blake3
py-cpuinfo
transformers >= 4.56.0, < 5
tokenizers >= 0.21.1  # Required for fast incremental detokenization.
protobuf # Required by LlamaTokenizer, gRPC.
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
aiohttp
openai >= 1.99.1  # For Responses API with reasoning content
pydantic >= 2.12.0
prometheus_client >= 0.18.0
pillow  # Required for image processing
prometheus-fastapi-instrumentator >= 7.0.0
tiktoken >= 0.6.0  # Required for DBRX tokenizer
lm-format-enforcer == 0.11.3
llguidance >= 1.3.0, < 1.4.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64" or platform_machine == "s390x" or platform_machine == "ppc64le"
outlines_core == 0.2.11
# required for outlines backend disk cache
diskcache == 5.6.3
lark == 1.2.2
xgrammar == 0.1.29; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64" or platform_machine == "s390x" or platform_machine == "ppc64le"
typing_extensions >= 4.10
filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
partial-json-parser # used for parsing partial JSON outputs
pyzmq >= 25.0.0
msgspec
gguf >= 0.17.0
mistral_common[image] >= 1.8.8
opencv-python-headless >= 4.13.0    # required for video IO
pyyaml
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
setuptools>=77.0.3,<81.0.0; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12
einops # Required for Qwen2-VL.
compressed-tensors == 0.13.0 # required for compressed-tensors
depyf==0.20.0 # required for profiling and debugging with compilation config
cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
watchfiles # required for http server to monitor the updates of TLS files
python-json-logger # Used by logging as per examples/others/logging_configuration.md
ninja # Required for xgrammar, rocm, tpu, xpu
pybase64 # fast base64 implementation
cbor2 # Required for cross-language serialization of hashable objects
ijson # Required for mistral streaming tool parser
setproctitle # Used to set process names for better debugging and monitoring
openai-harmony >= 0.0.3  # Required for gpt-oss
anthropic >= 0.71.0
model-hosting-container-standards >= 0.1.13, < 1.0.0
mcp
grpcio
grpcio-reflection