fix: vllm disagg launch script should not enable kv routing (#4063)

Signed-off-by: PeaBrane <[email protected]>

Author: PeaBrane

examples/backends/vllm/launch/disagg.sh

@@ -5,7 +5,7 @@ set -e
 trap 'echo Cleaning up...; kill 0' EXIT
 
 # run ingress
-python -m dynamo.frontend --router-mode kv --http-port=8000 &
+python -m dynamo.frontend --http-port=8000 &
 
 # --enforce-eager is added for quick deployment. for production use, need to remove this flag
 CUDA_VISIBLE_DEVICES=0 python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager &

examples/backends/vllm/launch/disagg_kvbm.sh

@@ -4,8 +4,8 @@
 set -e
 trap 'echo Cleaning up...; kill 0' EXIT
 
-# run ingress with KV router
-python -m dynamo.frontend --router-mode kv --http-port=8000 &
+# run ingress
+python -m dynamo.frontend --http-port=8000 &
 
 # run decode worker on GPU 0, without enabling KVBM
 # NOTE: remove --enforce-eager for production use