From 7bdc8b2de2b84040be69aadeb8c0bcb742d5e889 Mon Sep 17 00:00:00 2001 From: rock Date: Thu, 5 Nov 2026 09:22:48 +0800 Subject: [PATCH] fix(llm-serving): set runtimeClassName nvidia on the candle deployment Without it the container runs under runc, libcuda.so is never injected and candle-vllm panics in cudarc at startup. The pod reached Running but crashed on every restart. Verified live: pod Ready, coder-predictor endpoints populated, /v1/models reports coder-14b-fp16 and a completion returns OK. --- k8s/apps/llm-serving/coder-14b-fp16.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/k8s/apps/llm-serving/coder-14b-fp16.yaml b/k8s/apps/llm-serving/coder-14b-fp16.yaml index 69be1c4..f8f1f4a 100644 --- a/k8s/apps/llm-serving/coder-14b-fp16.yaml +++ b/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