mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-09 12:44:57 +08:00
47 lines
2.2 KiB
Plaintext
47 lines
2.2 KiB
Plaintext
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 >= 4.51.1
|
|
huggingface-hub[hf_xet] >= 0.32.0 # Required for Xet downloads.
|
|
tokenizers >= 0.21.1 # Required for fast incremental detokenization.
|
|
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 >= 2.10
|
|
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 >= 0.7.11, < 0.8.0; platform_machine == "x86_64" or platform_machine == "arm64" or platform_machine == "aarch64"
|
|
outlines == 0.1.11
|
|
lark == 1.2.2
|
|
xgrammar == 0.1.19; 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 >= 25.0.0
|
|
msgspec
|
|
gguf >= 0.13.0
|
|
importlib_metadata; python_version < '3.10'
|
|
mistral_common[opencv] >= 1.6.2
|
|
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>=77.0.3,<80; 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 == 0.10.1 # 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/others/logging_configuration.md
|
|
scipy # Required for phi-4-multimodal-instruct
|
|
ninja # Required for xgrammar, rocm, tpu, xpu
|