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, 22:35 UTC
[Misc] Remove upper bound in openai package version (#22060)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Woosuk Kwon committed
Aug 1, 2025 at 02:11 UTC
0f81b310db013ec9fbc1deb9de97bd9b2a9af62f
1 file changed
+1
-1
requirements/common.txt
+1
-1
@@ -13,7 +13,7 @@ tokenizers >= 0.21.1 # Required for fast incremental detokenization.
13
protobuf # Required by LlamaTokenizer.
14
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
15
aiohttp
16
-openai >= 1.87.0, <= 1.90.0 # Ensure modern openai package (ensure ResponsePrompt exists in type.responses and max_completion_tokens field support)
16
+openai >= 1.87.0 # Ensure modern openai package (ensure ResponsePrompt exists in type.responses and max_completion_tokens field support)
17
pydantic >= 2.10
18
prometheus_client >= 0.18.0
19
pillow # Required for image processing