Misc. bug: server not exit after `missing result_output tensor` error

[ngxson]

Name and Version

While testing the rerank model on HF inference endpoint, we got this error: GGML_ASSERT(strcmp(res->name, "result_output") == 0 && "missing result_output tensor") failed

This is due to missing LLAMA_ARG_RERANKING (for reranking model) or LLAMA_ARG_EMBEDDINGS (for embeddings model).

The application is expected to edit after this error, but it still running which makes it a bit confused for end user.

Expected behavior: the server should exit once it get that error.

Operating systems

No response

Which llama.cpp modules do you know to be affected?

No response

Command line

llama-server -m jina-rerank.gguf (do not add --rerank argument)

Problem description & steps to reproduce

Run a jina-rerank model without --rerank flag

First Bad Commit

No response

Relevant log output

(as seen on screenshot)