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