@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f954fe0e65
Fork 0

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, 04:30 UTC

[FIX] update openai version (#11287)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

Kunshang Ji committed Dec 19, 2024 at 02:17 UTC f954fe0e65cc078e62a40e8407f329996541d8c4
1 file changed +1 -1
requirements-common.txt
+1 -1
@@ -11,7 +11,7 @@ protobuf # Required by LlamaTokenizer.
11 fastapi >= 0.107.0, < 0.113.0; python_version < '3.9'
12 fastapi >= 0.107.0, != 0.113.*, != 0.114.0; python_version >= '3.9'
13 aiohttp
14 -openai >= 1.45.0 # Ensure modern openai package (ensure types module present and max_completion_tokens field support)
14 +openai >= 1.52.0 # Ensure modern openai package (ensure types module present and max_completion_tokens field support)
15 uvicorn[standard]
16 pydantic >= 2.9 # Required for fastapi >= 0.113.0
17 prometheus_client >= 0.18.0