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][misc] add note for Kubernetes users (#5916)
youkaichao committed
Jun 27, 2024 at 10:07 UTC
3fd02bda51ee7cf07e0375994ac1f34b6d1b981b
1 file changed
+2
docs/source/serving/env_vars.rst
+2
@@ -6,6 +6,8 @@ vLLM uses the following environment variables to configure the system:
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
+ All environment variables used by vLLM are prefixed with ``VLLM_``. **Special care should be taken for Kubernetes users**: please do not name the service as ``vllm``, otherwise environment variables set by Kubernetes might conflict with vLLM's environment variables, because `Kubernetes sets environment variables for each service with the capitalized service name as the prefix <https://kubernetes.io/docs/concepts/services-networking/service/#environment-variables>`_.
10
+
11
.. literalinclude:: ../../../vllm/envs.py
12
:language: python
13
:start-after: begin-env-vars-definition