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 17, 08:00 UTC
fix: freeze pydantic to v1 (#429)
Keming committed
Jul 12, 2023 at 23:10 UTC
51be365143382515a4be5f44d7ed9a900d5740b7
1 file changed
+1
-1
requirements.txt
+1
-1
@@ -8,5 +8,5 @@ transformers >= 4.28.0 # Required for LLaMA.
8
xformers >= 0.0.19
9
fastapi
10
uvicorn
11
-pydantic # Required for OpenAI server.
11
+pydantic < 2 # Required for OpenAI server.
12
fschat # Required for OpenAI ChatCompletion Endpoint.