cachetools
psutil
sentencepiece  # Required for LLaMA tokenizer.
numpy
requests >= 2.26.0
tqdm
blake3
py-cpuinfo
transformers >= 4.50.3
tokenizers >= 0.19.1  # Required for Llama 3.
protobuf # Required by LlamaTokenizer.
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
aiohttp
openai >= 1.52.0 # Ensure modern openai package (ensure types module present and max_completion_tokens field support)
pydantic >= 2.9
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 >= 0.10.11, < 0.11
llguidance >= 0.7.9, < 0.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64"
outlines == 0.1.11
lark == 1.2.2
xgrammar == 0.1.16; platform_machine == "x86_64" or platform_machine == "aarch64"
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
msgspec
gguf == 0.10.0
importlib_metadata
mistral_common[opencv] >= 1.5.4
opencv-python-headless >= 4.11.0    # 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>=74.1.1; 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 == 0.9.2 # required for compressed-tensors
depyf==0.18.0 # 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/other/logging_configuration.md
scipy # Required for phi-4-multimodal-instruct
ninja # Required for xgrammar, rocm, tpu, xpu