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 14, 05:30 UTC
[Misc] fix openai version (#22485)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
rongfu.leng committed
Aug 8, 2025 at 16:12 UTC
904063907c141fe59c2302afe5bc94cbb53c0de6
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -12,7 +12,7 @@ tokenizers >= 0.21.1 # Required for fast incremental detokenization.
12
protobuf # Required by LlamaTokenizer.
13
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
14
aiohttp
15
-openai >= 1.98.0 # For Responses API with reasoning content
15
+openai >= 1.99.1 # For Responses API with reasoning content
16
pydantic >= 2.10
17
prometheus_client >= 0.18.0
18
pillow # Required for image processing