@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 294104c3f9
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, 23:15 UTC

[doc] update usage of env var to avoid conflict (#5873)

youkaichao committed Jun 26, 2024 at 14:57 UTC 294104c3f9ab471d2d571b6a6eda266af3824d6a
1 file changed +3
docs/source/serving/env_vars.rst
+3
@@ -3,6 +3,9 @@ Environment Variables
3
4 vLLM uses the following environment variables to configure the system:
5
6 +.. warning::
7 + Please note that ``VLLM_PORT`` and ``VLLM_HOST_IP`` set the port and ip for vLLM's **internal usage**. It is not the port and ip for the API server. If you use ``--host $VLLM_HOST_IP`` and ``--port $VLLM_PORT`` to start the API server, it will not work.
8 +
9 .. literalinclude:: ../../../vllm/envs.py
10 :language: python
11 :start-after: begin-env-vars-definition