From eb211d5ada941b823a815b6321dd88ddcadac7ba Mon Sep 17 00:00:00 2001 From: youkaichao Date: Tue, 23 Jul 2024 08:51:46 -0700 Subject: [PATCH] fix doc --- docs/source/serving/distributed_serving.rst | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/source/serving/distributed_serving.rst b/docs/source/serving/distributed_serving.rst index ff91f73f277d..4fc36a680084 100644 --- a/docs/source/serving/distributed_serving.rst +++ b/docs/source/serving/distributed_serving.rst @@ -66,8 +66,8 @@ Pick a node as the head node, and run the following command: $ bash run_cluster.sh \ $ vllm/vllm-openai \ $ ip_of_head_node \ - $ /path/to/the/huggingface/home/in/this/node \ - $ --head + $ --head \ + $ /path/to/the/huggingface/home/in/this/node On the rest of the worker nodes, run the following command: @@ -76,8 +76,8 @@ On the rest of the worker nodes, run the following command: $ bash run_cluster.sh \ $ vllm/vllm-openai \ $ ip_of_head_node \ - $ /path/to/the/huggingface/home/in/this/node \ - $ --worker + $ --worker \ + $ /path/to/the/huggingface/home/in/this/node Then you get a ray cluster of containers. Note that you need to keep the shells running these commands alive to hold the cluster. Any shell disconnect will terminate the cluster.