mirror of https://github.com/vllm-project/vllm
35 lines
1.4 KiB
Plaintext
35 lines
1.4 KiB
Plaintext
psutil
|
|
sentencepiece # Required for LLaMA tokenizer.
|
|
numpy < 2.0.0
|
|
requests >= 2.26.0
|
|
tqdm
|
|
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 >= 1.40.0 # Ensure modern openai package (ensure types module present)
|
|
uvicorn[standard]
|
|
pydantic >= 2.9 # Required for fastapi >= 0.113.0
|
|
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
|
|
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 == 0.10.0
|
|
importlib_metadata
|
|
mistral_common[opencv] >= 1.4.4
|
|
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 == 0.7.1 # required for compressed-tensors
|