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

Add MLP & QLoRA Fused Ops and Kernels, Mixtral #29

Merged
merged 12 commits into from
Jun 2, 2024
Merged

Add MLP & QLoRA Fused Ops and Kernels, Mixtral #29

merged 12 commits into from
Jun 2, 2024

Commits on May 30, 2024

  1. refactor 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    073e23b View commit details
    Browse the repository at this point in the history

  2. fixes 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    4fa64fe View commit details
    Browse the repository at this point in the history

  3. refactor mistral 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    fb81605 View commit details
    Browse the repository at this point in the history

  4. add mixtral 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    0fd8b0e View commit details
    Browse the repository at this point in the history

  5. some refactoring after introducing mlp 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    0e41679 View commit details
    Browse the repository at this point in the history

  6. remove extranous files 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    3f03ce4 View commit details
    Browse the repository at this point in the history

  7. add bnb 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    97f013c View commit details
    Browse the repository at this point in the history

  8. lint + fmt and improvements to readme 

    Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
    @fabianlim
    fabianlim committed May 30, 2024
    Configuration menu
    Copy the full SHA
    a308a61 View commit details
    Browse the repository at this point in the history

Commits on May 31, 2024

  1. bench fixes

    @fabianlim
    fabianlim committed May 31, 2024
    Configuration menu
    Copy the full SHA
    435d685 View commit details
    Browse the repository at this point in the history

  2. need to handle lora adapters device due to foundation-model-stack#26

    @fabianlim
    fabianlim committed May 31, 2024
    Configuration menu
    Copy the full SHA
    f666d5e View commit details
    Browse the repository at this point in the history

Commits on Jun 1, 2024

  1. allow replay of failed benches, addressing comment in foundation-mode… 

    …l-stack#14
    @fabianlim
    fabianlim committed Jun 1, 2024
    Configuration menu
    Copy the full SHA
    77bc92b View commit details
    Browse the repository at this point in the history

  2. update benches (remove l40)

    @fabianlim
    fabianlim committed Jun 1, 2024
    Configuration menu
    Copy the full SHA
    2f98563 View commit details
    Browse the repository at this point in the history