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]