diff --git a/k8s/apps/llm-serving/clef-flash.yaml b/k8s/apps/llm-serving/clef-flash.yaml
index c2749bf..8a71e23 100644
--- a/k8s/apps/llm-serving/clef-flash.yaml
+++ b/k8s/apps/llm-serving/clef-flash.yaml
@@ -53,6 +53,10 @@ spec:
       # layers use linear attention and hold a fixed 48 MiB state regardless
       # of length. Memory is therefore dominated by the BF16 weights (18.8 GB),
       # not the cache, which is why one V100-32GB is enough.
+      # The image ships its CLI at /opt/sglang/bin/sglang and puts no `serve` on
+      # PATH, so a bare `serve` failed with "exec: serve: not found" on every start
+      # (19 restarts). Name the binary by its full path.
+      - /opt/sglang/bin/sglang
       - serve
       - --model-path=Cloudflare/clef-flash
       - --host=0.0.0.0