"vscode:/vscode.git/clone" did not exist on "5b193f9b7c2e8485b62a8fdf48fdd576a4174eae"
Unverified Commit 3aec3d4f authored by Bruce-x-1997's avatar Bruce-x-1997 Committed by GitHub
Browse files

[Doc] add LWS(LeaderWorkerSet) use case in sgl-router README (#9568)


Co-authored-by: default avatarbruce.xu <bruce.xu@gmicloud.ai>
parent e3e97a12
...@@ -229,6 +229,15 @@ python -m sglang_router.launch_router \ ...@@ -229,6 +229,15 @@ python -m sglang_router.launch_router \
--prefill-selector app=sglang component=prefill \ --prefill-selector app=sglang component=prefill \
--decode-selector app=sglang component=decode \ --decode-selector app=sglang component=decode \
--service-discovery-namespace sglang-system --service-discovery-namespace sglang-system
# in lws case, such as tp16(1 leader pod, 1 worker pod)
python -m sglang_router.launch_router \
--pd-disaggregation \
--policy cache_aware \
--service-discovery \
--prefill-selector app=sglang component=prefill role=leader\
--decode-selector app=sglang component=decode role=leader\
--service-discovery-namespace sglang-system
``` ```
#### Kubernetes Pod Configuration #### Kubernetes Pod Configuration
......
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