Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: ggml-org/llama.cpp
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master
Choose a base ref
...
head repository: ggml-org/llama.cpp
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: scratch
Choose a head ref
  • 15 commits
  • 3 files changed
  • 1 contributor

Commits on Oct 28, 2023

  1. llama : factor out ggml-alloc from graph graph build functions 

    ggml-ci
    @ggerganov
    ggerganov committed Oct 28, 2023
    Configuration menu
    Copy the full SHA
    8b2420d View commit details
    Browse the repository at this point in the history

  2. metal : disable kernel load log

    @ggerganov
    ggerganov committed Oct 28, 2023
    Configuration menu
    Copy the full SHA
    5946d98 View commit details
    Browse the repository at this point in the history

  3. llama : factor out tensor offloading outside the build call (wip) 

    ggml-ci
    @ggerganov
    ggerganov committed Oct 28, 2023
    Configuration menu
    Copy the full SHA
    38aca9e View commit details
    Browse the repository at this point in the history

  4. llama : offload rest of the models 

    ggml-ci
    @ggerganov
    ggerganov committed Oct 28, 2023
    Configuration menu
    Copy the full SHA
    83d2c43 View commit details
    Browse the repository at this point in the history

  5. llama : update offload log messages to print node index

    @ggerganov
    ggerganov committed Oct 28, 2023
    Configuration menu
    Copy the full SHA
    3af8771 View commit details
    Browse the repository at this point in the history

  6. llama : comments

    @ggerganov
    ggerganov committed Oct 28, 2023
    Configuration menu
    Copy the full SHA
    51c4f9e View commit details
    Browse the repository at this point in the history

Commits on Oct 29, 2023

  1. llama : support offloading result_norm + comments

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    4e98897 View commit details
    Browse the repository at this point in the history

  2. llama : factor graph input into a function

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    0dc05b8 View commit details
    Browse the repository at this point in the history

  3. llama : do tensor offload only with CUDA

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    e14aa46 View commit details
    Browse the repository at this point in the history

  4. llama : fix res_norm offloading

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    7961790 View commit details
    Browse the repository at this point in the history

  5. llama : try to optimize offloading code

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    b4ad03b View commit details
    Browse the repository at this point in the history

  6. llama : fix non-CUDA build

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    25cfbf6 View commit details
    Browse the repository at this point in the history

  7. llama : try to fix build

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    739b85c View commit details
    Browse the repository at this point in the history

  8. llama : move refact in correct place + optimize graph input

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    da93618 View commit details
    Browse the repository at this point in the history

  9. llama : refactor tensor offloading as callback

    @ggerganov
    ggerganov committed Oct 29, 2023
    Configuration menu
    Copy the full SHA
    1526719 View commit details
    Browse the repository at this point in the history
Loading