Found while testing #117 live.
A served LLMModel's vllm pod crashloops immediately:
/opt/nvidia/nvidia_entrypoint.sh: line 67: exec: --: invalid option
operator/internal/controller/reconcilers/modelservice.go sets the vllm container's Args (the vLLM flags: --model, --served-model-name, ...) but no Command. ghcr.io/llm-d/llm-d-cuda:v0.7.0 has Entrypoint: ["/opt/nvidia/nvidia_entrypoint.sh"] and no default CMD, so the wrapper exec's the flags as if they were the command and exits.
Impact: served models never start on the default serving image.
Fix: set the container Command to the standard vLLM OpenAI-server entrypoint (python3 -m vllm.entrypoints.openai.api_server); the image's venv python is on PATH. Done on the #117 branch (commit c512e37) with a test asserting the command is set.
Found while testing #117 live.
A served
LLMModel'svllmpod crashloops immediately:operator/internal/controller/reconcilers/modelservice.gosets thevllmcontainer'sArgs(the vLLM flags:--model,--served-model-name, ...) but noCommand.ghcr.io/llm-d/llm-d-cuda:v0.7.0hasEntrypoint: ["/opt/nvidia/nvidia_entrypoint.sh"]and no defaultCMD, so the wrapper exec's the flags as if they were the command and exits.Impact: served models never start on the default serving image.
Fix: set the container
Commandto the standard vLLM OpenAI-server entrypoint (python3 -m vllm.entrypoints.openai.api_server); the image's venv python is on PATH. Done on the #117 branch (commit c512e37) with a test asserting the command is set.