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