k8s/apps/llm-serving/coder-14b-fp16.yaml

@@ -60,6 +60,10 @@ spec:
         app.kubernetes.io/part-of: llm-serving
         app: candle-vllm
     spec:
+      # Required. Without this the container runs under runc, libcuda.so is never
+      # injected, and candle-vllm panics in cudarc at startup with
+      # "Unable to dynamically load the cuda shared library".
+      runtimeClassName: nvidia
       containers:
         - name: candle
           image: forgejo.riotpiao.com/riotpiao-poimen/candle-vllm:sm70-gptq-slim