KBaba7/llama.cpp

1name: Bug (model use)2description: Something goes wrong when using a model (in general, not specific to a single llama.cpp module).3title: "Eval bug: "4labels: ["bug-unconfirmed", "model evaluation"]5body:6  - type: markdown7    attributes:8      value: >9        Thanks for taking the time to fill out this bug report!10        This issue template is intended for bug reports where the model evaluation results11        (i.e. the generated text) are incorrect or llama.cpp crashes during model evaluation.12        If you encountered the issue while using an external UI (e.g. ollama),13        please reproduce your issue using one of the examples/binaries in this repository.14        The `llama-cli` binary can be used for simple and reproducible model inference.15  - type: textarea16    id: version17    attributes:18      label: Name and Version19      description: Which version of our software are you running? (use `--version` to get a version string)20      placeholder: |21        $./llama-cli --version22        version: 2999 (42b4109e)23        built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu24    validations:25      required: true26  - type: dropdown27    id: operating-system28    attributes:29      label: Operating systems30      description: Which operating systems do you know to be affected?31      multiple: true32      options:33        - Linux34        - Mac35        - Windows36        - BSD37        - Other? (Please let us know in description)38    validations:39      required: true40  - type: dropdown41    id: backends42    attributes:43        label: GGML backends44        description: Which GGML backends do you know to be affected?45        options: [AMX, BLAS, CPU, CUDA, HIP, Kompute, Metal, Musa, RPC, SYCL, Vulkan]46        multiple: true47    validations:48      required: true49  - type: textarea50    id: hardware51    attributes:52      label: Hardware53      description: Which CPUs/GPUs are you using?54      placeholder: >55        e.g. Ryzen 5950X + 2x RTX 409056    validations:57      required: true58  - type: textarea59    id: model60    attributes:61      label: Models62      description: >63        Which model(s) at which quantization were you using when encountering the bug?64        If you downloaded a GGUF file off of Huggingface, please provide a link.65      placeholder: >66        e.g. Meta LLaMA 3.1 Instruct 8b q4_K_M67    validations:68      required: false69  - type: textarea70    id: info71    attributes:72      label: Problem description & steps to reproduce73      description: >74        Please give us a summary of the problem and tell us how to reproduce it.75        If you can narrow down the bug to specific hardware, compile flags, or command line arguments,76        that information would be very much appreciated by us.77      placeholder: >78        e.g. when I run llama-cli with -ngl 99 I get garbled outputs.79        When I use -ngl 0 it works correctly.80        Here are the exact commands that I used: ...81    validations:82      required: true83  - type: textarea84    id: first_bad_commit85    attributes:86      label: First Bad Commit87      description: >88        If the bug was not present on an earlier version: when did it start appearing?89        If possible, please do a git bisect and identify the exact commit that introduced the bug.90    validations:91      required: false92  - type: textarea93    id: logs94    attributes:95      label: Relevant log output96      description: >97          Please copy and paste any relevant log output, including the command that you entered and any generated text.98          This will be automatically formatted into code, so no need for backticks.99      render: shell100    validations:101      required: true102