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, 22:00 UTC
[doc][misc] further lower visibility of simple api server (#6041)
Co-authored-by: Simon Mo <simon.mo@hey.com>
youkaichao committed
Jul 1, 2024 at 10:50 UTC
8893130b63e6b2778b5d3db4dbc83ff6206ba44a
1 file changed
+6
-1
examples/api_client.py
+6
-1
@@ -1,4 +1,9 @@
1
-"""Example Python client for vllm.entrypoints.api_server"""
1
+"""Example Python client for vllm.entrypoints.api_server
2
+NOTE: The API server is used only for demonstration and simple performance
3
+benchmarks. It is not intended for production use.
4
+For production use, we recommend vllm.entrypoints.openai.api_server
5
+and the OpenAI client API
6
+"""
7
8
import argparse
9
import json