server/common : segmentation faults when loading LoRA adapter fails

[nmouha]

Overview

Loading an invalid LoRA adapter causes a null pointer dereference in llama-server, and a use-after-free in llama-completion.

Additional information

To reproduce:

echo "BAD!" > bad.gguf
llama-server -hf ggml-org/models-moved --lora bad.gguf
llama-completion -hf ggml-org/models-moved --lora bad.gguf

Requirements

• I have read and agree with the contributing guidelines
• AI usage disclosure:

NO

[ggml-gh-bot]

Hi @nmouha, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

• PR Template not respected: Please respect the template when creating a new pull request. Make sure to fill out all required sections.

---

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.