vllm/requirements-common.txt

cmake >= 3.21
ninja  # For faster builds.
psutil
sentencepiece  # Required for LLaMA tokenizer.
numpy
requests
py-cpuinfo
transformers >= 4.39.1  # Required for StarCoder2 & Llava.
fastapi
uvicorn[standard]
pydantic >= 2.0  # Required for OpenAI server.
prometheus_client >= 0.18.0
tiktoken == 0.6.0  # Required for DBRX tokenizer
outlines == 0.0.34  # Requires torch >= 2.1.0
[Misc] Define common requirements (#3841) 2024-04-05 15:39:17 +08:00			`cmake >= 3.21`
Specify python package dependencies in requirements.txt (#78) 2023-05-08 07:30:43 +08:00			`ninja # For faster builds.`
			`psutil`
			`sentencepiece # Required for LLaMA tokenizer.`
			`numpy`
Usage Stats Collection (#2852) 2024-03-29 13:16:12 +08:00			`requests`
			`py-cpuinfo`
[Misc] Bump transformers version (#3592) 2024-03-24 21:32:45 +08:00			`transformers >= 4.39.1 # Required for StarCoder2 & Llava.`
Specify python package dependencies in requirements.txt (#78) 2023-05-08 07:30:43 +08:00			`fastapi`
Use standard extras for uvicorn (#1166) 2023-09-28 08:41:36 +08:00			`uvicorn[standard]`
migrate pydantic from v1 to v2 (#2531) 2024-01-22 08:05:56 +08:00			`pydantic >= 2.0 # Required for OpenAI server.`
Restrict prometheus_client >= 0.18.0 to prevent errors when importing pkgs (#3070) 2024-02-28 13:38:26 +08:00			`prometheus_client >= 0.18.0`
[Misc] Define common requirements (#3841) 2024-04-05 15:39:17 +08:00			`tiktoken == 0.6.0 # Required for DBRX tokenizer`
			`outlines == 0.0.34 # Requires torch >= 2.1.0`