@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 3f79bc3d1a
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

[Bugfix] Bump fastapi and pydantic version (#8435)

Cyrus Leung committed Sep 13, 2024 at 11:21 UTC 3f79bc3d1a65b7ed266702bb745c66b10283361f
1 file changed +2 -2
requirements-common.txt
+2 -2
@@ -7,11 +7,11 @@ 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
10 +fastapi >= 0.114.1
11 aiohttp
12 openai >= 1.40.0 # Ensure modern openai package (ensure types module present)
13 uvicorn[standard]
14 -pydantic >= 2.8 # Required for OpenAI server.
14 +pydantic >= 2.9 # Required for fastapi >= 0.113.0
15 pillow # Required for image processing
16 prometheus_client >= 0.18.0
17 prometheus-fastapi-instrumentator >= 7.0.0