Skip to content

GitLab

Unverified Commit 29b97c09 authored by Ning Xie's avatar Ning Xie Committed by GitHub
Browse files

[Doc] add backend to doc string of initialize_model_parallel (#22142) 


Signed-off-by: default avatarAndy Xie <andy.xning@gmail.com>
parent 7b455cf1
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
vllm/distributed/parallel_state.py
View file @ 29b97c09
...@@ -1013,6 +1013,7 @@ def initialize_model_parallel( ...@@ -1013,6 +1013,7 @@ def initialize_model_parallel(
parallelism. parallelism.
pipeline_model_parallel_size: number of GPUs used for pipeline model pipeline_model_parallel_size: number of GPUs used for pipeline model
parallelism. parallelism.
backend: name of torch distributed communication backend.
Let's say we have a total of 8 GPUs denoted by g0 ... g7 and we Let's say we have a total of 8 GPUs denoted by g0 ... g7 and we
use 2 GPUs to parallelize the model tensor, and 4 GPUs to parallelize use 2 GPUs to parallelize the model tensor, and 4 GPUs to parallelize
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment