psutil
sentencepiece  # Required for LLaMA tokenizer.
numpy < 2.0.0
requests >= 2.26.0
tqdm
blake3
py-cpuinfo
transformers >= 4.45.2  # Required for Llama 3.2 and Qwen2-VL.
tokenizers >= 0.19.1  # Required for Llama 3.
protobuf # Required by LlamaTokenizer.
fastapi >= 0.107.0, < 0.113.0; python_version < '3.9'
fastapi >= 0.107.0, != 0.113.*, != 0.114.0; python_version >= '3.9'
aiohttp
openai >= 1.52.0 # Ensure modern openai package (ensure types module present and max_completion_tokens field support)
uvicorn[standard]
pydantic >= 2.9  # Required for fastapi >= 0.113.0
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 >= 0.10.9, < 0.11
outlines == 0.1.11
lark == 1.2.2 
xgrammar >= 0.1.6; platform_machine == "x86_64"
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] >= 1.5.0
pyyaml
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
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 == 0.9.0 # 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
ray[default] >= 2.9
nvidia-ml-py >= 12.560.30 # for pynvml package