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 7, 00:15 UTC
[ci] Bound openai dependency to 2.24.0 (#36471)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Kevin H. Luu committed
Mar 9, 2026 at 03:43 UTC
aaf5fa9abfb7c265ccfe00480c349870a72b7209
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 >= 5.29.6, !=6.30.*, !=6.31.*, !=6.32.*, !=6.33.0.*, !=6.33.1.*, !=6.33.2.*, !=6.33.3.*, !=6.33.4.* # Required by LlamaTokenizer, gRPC. CVE-2026-0994
13
fastapi[standard] >= 0.115.0 # Required by FastAPI's form models in the OpenAI API server's audio transcriptions endpoint.
14
aiohttp >= 3.13.3
15
-openai >= 1.99.1 # For Responses API with reasoning content
15
+openai >= 1.99.1, < 2.25.0 # For Responses API with reasoning content
16
pydantic >= 2.12.0
17
prometheus_client >= 0.18.0
18
pillow # Required for image processing