@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / ecd7a1d5b6
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 17:00 UTC

[Installation] Gate FastAPI version for Python 3.8 (#8456)

Cyrus Leung committed Sep 14, 2024 at 00:02 UTC ecd7a1d5b69589257d36626195ece6658b61b93c
1 file changed +2 -1
requirements-common.txt
+2 -1
@@ -7,7 +7,8 @@ py-cpuinfo
7 transformers >= 4.43.2 # Required for Chameleon and Llama 3.1 hotfox.
8 tokenizers >= 0.19.1 # Required for Llama 3.
9 protobuf # Required by LlamaTokenizer.
10 -fastapi >= 0.114.1
10 +fastapi < 0.113.0; python_version < '3.9'
11 +fastapi >= 0.114.1; python_version >= '3.9'
12 aiohttp
13 openai >= 1.40.0 # Ensure modern openai package (ensure types module present)
14 uvicorn[standard]