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

backend : offload large batches to GPU #6083

Merged
merged 9 commits into from
Mar 18, 2024
Merged

backend : offload large batches to GPU #6083

merged 9 commits into from
Mar 18, 2024

Commits on Mar 16, 2024

  1. backend : offload large batches to GPU

    @slaren
    slaren committed Mar 16, 2024
    Configuration menu
    Copy the full SHA
    5b6b4ac View commit details
    Browse the repository at this point in the history

  2. fix hip

    @slaren
    slaren committed Mar 16, 2024
    Configuration menu
    Copy the full SHA
    c2dba04 View commit details
    Browse the repository at this point in the history

  3. code cleanup

    @slaren
    slaren committed Mar 16, 2024
    Configuration menu
    Copy the full SHA
    3a77442 View commit details
    Browse the repository at this point in the history

  4. fix CUDA split buffers

    @slaren
    slaren committed Mar 16, 2024
    Configuration menu
    Copy the full SHA
    c0fe629 View commit details
    Browse the repository at this point in the history

  5. Update ggml-backend-impl.h 

    Co-authored-by: Johannes Gäßler <[email protected]>
    @slaren @JohannesGaessler
    slaren and JohannesGaessler authored Mar 16, 2024
    Configuration menu
    Copy the full SHA
    8e717e8 View commit details
    Browse the repository at this point in the history

  6. cuda : fix memset without set_device

    @slaren
    slaren committed Mar 16, 2024
    Configuration menu
    Copy the full SHA
    9cba8a1 View commit details
    Browse the repository at this point in the history

  7. imatrix : remove sched affix from weight names

    @slaren
    slaren committed Mar 16, 2024
    Configuration menu
    Copy the full SHA
    9809075 View commit details
    Browse the repository at this point in the history

Commits on Mar 17, 2024

  1. sched : add a new split if the current one has too many inputs 

    reduce max inputs per split
more cleanup
    @slaren
    slaren committed Mar 17, 2024
    Configuration menu
    Copy the full SHA
    0661e6a View commit details
    Browse the repository at this point in the history

  2. update backends 

    ggml-ci
    @slaren
    slaren committed Mar 17, 2024
    Configuration menu
    Copy the full SHA
    cc9299c View commit details
    Browse the repository at this point in the history