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