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] >1.43 constraint for openai (#8169)
Co-authored-by: Michael Goin <michael@neuralmagic.com>
William Lin committed
Sep 4, 2024 at 17:35 UTC
1afc931987d0c0e12bb3fde7908e768222916385
1 file changed
+1
-1
requirements-common.txt
+1
-1
@@ -9,7 +9,7 @@ tokenizers >= 0.19.1 # Required for Llama 3.
9
protobuf # Required by LlamaTokenizer.
10
fastapi
11
aiohttp
12
-openai >= 1.0 # Ensure modern openai package (ensure types module present)
12
+openai >= 1.40.0 # Ensure modern openai package (ensure types module present)
13
uvicorn[standard]
14
pydantic >= 2.8 # Required for OpenAI server.
15
pillow # Required for image processing