char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Johannes GäßlerGithub: update issue templates (#22594)9dbb37261

char/aliceai-t5-moe
brancheschar/aliceai-t5-moeall refs →
3.3 KiB90 linesraw
1name: Bug (compilation)
2description: Something goes wrong when trying to compile llama.cpp.
3title: "Compile bug: "
4labels: ["bug-unconfirmed", "compilation"]
5body:
6  - type: markdown
7    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 compilation of llama.cpp fails.
11        Before opening an issue, please confirm that the compilation still fails
12        after recreating the CMake build directory and with `-DGGML_CCACHE=OFF`.
13        If the compilation succeeds with ccache disabled you should be able to permanently fix the issue
14        by clearing `~/.cache/ccache` (on Linux).
15
16        Please fill out this template yourself, copypasting language model outputs is [strictly prohibited](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md#ai-usage-policy).
17  - type: textarea
18    id: commit
19    attributes:
20      label: Git commit
21      description: Which commit are you trying to compile?
22      placeholder: |
23        $git rev-parse HEAD
24        84a07a17b1b08cf2b9747c633a2372782848a27f
25    validations:
26      required: true
27  - type: dropdown
28    id: operating-system
29    attributes:
30      label: Operating systems
31      description: Which operating systems do you know to be affected?
32      multiple: true
33      options:
34        - Linux
35        - Mac
36        - Windows
37        - BSD
38        - Other? (Please let us know in description)
39    validations:
40      required: true
41  - type: dropdown
42    id: backends
43    attributes:
44        label: GGML backends
45        description: Which GGML backends do you know to be affected?
46        options: [AMX, BLAS, CANN, CPU, CUDA, Hexagon, HIP, Metal, Musa, OpenCL, OpenVINO, RPC, SYCL, VirtGPU, Vulkan, WebGPU, zDNN, ZenDNN]
47        multiple: true
48    validations:
49      required: true
50  - type: textarea
51    id: info
52    attributes:
53      label: Problem description & steps to reproduce
54      description: >
55        Please give us a summary of the problem and tell us how to reproduce it.
56        If you can narrow down the bug to specific compile flags, that information would be very much appreciated by us.
57      placeholder: >
58        I'm trying to compile llama.cpp with CUDA support on a fresh install of Ubuntu and get error XY.
59        Here are the exact commands that I used: ...
60    validations:
61      required: true
62  - type: textarea
63    id: first_bad_commit
64    attributes:
65      label: First Bad Commit
66      description: >
67        If the bug was not present on an earlier version: when did it start appearing?
68        If possible, please do a git bisect and identify the exact commit that introduced the bug.
69    validations:
70      required: false
71  - type: textarea
72    id: command
73    attributes:
74      label: Compile command
75      description: >
76        Please provide the exact command you used to compile llama.cpp. For example: `cmake -B ...`.
77        This will be automatically formatted into code, so no need for backticks.
78      render: shell
79    validations:
80      required: true
81  - type: textarea
82    id: logs
83    attributes:
84      label: Relevant log output
85      description: >
86          Please copy and paste any relevant log output, including any generated text.
87          This will be automatically formatted into code, so no need for backticks.
88      render: shell
89    validations:
90      required: true