fix: add --is-decode-worker flag (#5843)

Signed-off-by: Hannah Zhang <hannahz@nvidia.com>

fix: add --is-decode-worker flag (#5843)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
6c870810 · hhzhang16 · GitHub · b88cb59b · 6c870810
Unverified Commit 6c870810 authored Jan 30, 2026 by hhzhang16 Committed by GitHub Jan 30, 2026
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

examples/basics/kubernetes/Distributed_Inference/disagg_router.yaml ...asics/kubernetes/Distributed_Inference/disagg_router.yaml +1 -1

No files found.
--- a/examples/basics/kubernetes/Distributed_Inference/disagg_router.yaml
+++ b/examples/basics/kubernetes/Distributed_Inference/disagg_router.yaml
@@ -42,7 +42,7 @@ spec:
            - /bin/sh
            - -c
          args:
-            - python3 -m dynamo.vllm --model meta-llama/Llama-3.1-70B-Instruct -tp 8
+            - python3 -m dynamo.vllm --model meta-llama/Llama-3.1-70B-Instruct -tp 8 --is-decode-worker
    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker