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, 15:45 UTC
[Installation] Allow lower versions of FastAPI to maintain Ray 2.9 compatibility (#8764)
Cyrus Leung committed
Sep 27, 2024 at 07:54 UTC
1b49148e474d4d18731e159ea0460145ae52e220
1 file changed
+2
-2
requirements-common.txt
+2
-2
@@ -7,8 +7,8 @@ py-cpuinfo
7
transformers >= 4.45.0 # Required for Llama 3.2.
8
tokenizers >= 0.19.1 # Required for Llama 3.
9
protobuf # Required by LlamaTokenizer.
10
-fastapi < 0.113.0; python_version < '3.9'
11
-fastapi >= 0.114.1; python_version >= '3.9'
10
+fastapi >= 0.107.0, < 0.113.0; python_version < '3.9'
11
+fastapi >= 0.107.0, != 0.113.*, != 0.114.0; python_version >= '3.9'
12
aiohttp
13
openai >= 1.40.0 # Ensure modern openai package (ensure types module present)
14
uvicorn[standard]