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] remove deprecated api server in doc (#6037)
youkaichao committed
Jul 1, 2024 at 09:52 UTC
4050d646e5221a516c93384b047e10b22d7167e7
1 file changed
+1
-1
docs/source/serving/distributed_serving.rst
+1
-1
@@ -19,7 +19,7 @@ To run multi-GPU serving, pass in the :code:`--tensor-parallel-size` argument wh
19
20
.. code-block:: console
21
22
- $ python -m vllm.entrypoints.api_server \
22
+ $ python -m vllm.entrypoints.openai.api_server \
23
$ --model facebook/opt-13b \
24
$ --tensor-parallel-size 4
25