diff --git a/components/backends/sglang/deploy/disagg.yaml b/components/backends/sglang/deploy/disagg.yaml index 06c4b842d2..aa90223486 100644 --- a/components/backends/sglang/deploy/disagg.yaml +++ b/components/backends/sglang/deploy/disagg.yaml @@ -83,7 +83,7 @@ spec: args: - "python3" - "-m" - - "dynamo.sglang.worker" + - "dynamo.sglang.decode_worker" - "--model-path" - "deepseek-ai/DeepSeek-R1-Distill-Llama-8B" - "--served-model-name" @@ -152,4 +152,4 @@ spec: - "--disaggregation-mode" - "prefill" - "--disaggregation-transfer-backend" - - "nixl" \ No newline at end of file + - "nixl" diff --git a/components/backends/sglang/launch/agg_router.sh b/components/backends/sglang/launch/agg_router.sh index b45509235c..46a0eff19d 100755 --- a/components/backends/sglang/launch/agg_router.sh +++ b/components/backends/sglang/launch/agg_router.sh @@ -15,7 +15,8 @@ trap cleanup EXIT INT TERM python3 -m dynamo.sglang.utils.clear_namespace --namespace dynamo # run ingress -dynamo run in=http out=dyn --router-mode kv --http-port=8000 & +# run ingress +python -m dynamo.frontend --router-mode kv --http-port=8000 & DYNAMO_PID=$! # run worker