Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

sync : llama.cpp #981

Merged
merged 9 commits into from
Oct 3, 2024
Merged

sync : llama.cpp #981

merged 9 commits into from
Oct 3, 2024

Commits on Oct 3, 2024

  1. vulkan : do not use tensor->extra (llama/9407) 

    * vulkan : do not use tensor->extra

This patch allows using the Vulkan backend with the RPC backend as
tensor->extra is no longer used.

Ref: #8536

* Adapt GGML_VULKAN_CHECK_RESULTS to extra removal (llama/2)

---------

Co-authored-by: 0cc4m <picard12@live.de>
    @rgerganov @0cc4m @ggerganov
    2 people authored and ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    b7b8c8d View commit details
    Browse the repository at this point in the history

  2. Initial cmake support of SYCL for AMD GPUs (llama/9658) 

    sycl: initial cmake support of SYCL for AMD GPUs
    @Alcpz @ggerganov
    Alcpz authored and ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    bd0f0fc View commit details
    Browse the repository at this point in the history

  3. ggml-backend : add device and backend reg interfaces (llama/9707) 

    Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
    @slaren @JohannesGaessler @ggerganov
    2 people authored and ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    8b5ef87 View commit details
    Browse the repository at this point in the history

  4. Fixed dequant precision issues in Q4_1 and Q5_1 (llama/9711)

    @OuadiElfarouki @ggerganov
    OuadiElfarouki authored and ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    333e1b9 View commit details
    Browse the repository at this point in the history

  5. sync : llama.cpp

    @ggerganov
    ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    0b99d4a View commit details
    Browse the repository at this point in the history

  6. ggml-backend : add device and backend reg interfaces (llama/9707) 

    Also:

- metal : fix compute pass descriptor autorelease crash
- ggml-backend : add device description to CPU backend
- ggml: unify backend logging mechanism
    @slaren @ggerganov
    slaren authored and ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    034e36f View commit details
    Browse the repository at this point in the history

  7. examples : adapt to new ggml backend interfaces 

    ggml-ci
    @ggerganov
    ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    11279f9 View commit details
    Browse the repository at this point in the history

  8. cont : fixes

    @ggerganov
    ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    0b948fc View commit details
    Browse the repository at this point in the history

  9. ggml : remove old file (skip) (#0)

    @ggerganov
    ggerganov committed Oct 3, 2024
    Configuration menu
    Copy the full SHA
    9e764b7 View commit details
    Browse the repository at this point in the history