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

(wip) add Flash decoding #5

Open
wants to merge 15 commits into
base: master
Choose a base branch
from
Open

(wip) add Flash decoding #5

wants to merge 15 commits into from

Commits on Jan 20, 2024

  1. Merge pull request #2 from ggerganov/master 

    Merge with llamacpp master
    @calvintwr
    calvintwr authored Jan 20, 2024
    Configuration menu
    Copy the full SHA
    c3bc00c View commit details
    Browse the repository at this point in the history

Commits on Jan 23, 2024

  1. Merge branch 'ggerganov:master' into master

    @FSSRepo
    FSSRepo authored Jan 23, 2024
    Configuration menu
    Copy the full SHA
    dc5d269 View commit details
    Browse the repository at this point in the history

Commits on Mar 6, 2024

  1. Merge branch 'master' of https://github.com/Pints-App/llama.cpp

    @FSSRepo
    FSSRepo committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    c42f7cb View commit details
    Browse the repository at this point in the history

  2. cleanup FA implementation + flash decoding kernel (wip)

    @FSSRepo
    FSSRepo committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    888a724 View commit details
    Browse the repository at this point in the history

Commits on Mar 7, 2024

  1. fix NaNs when context reset

    @FSSRepo
    FSSRepo committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    936cea0 View commit details
    Browse the repository at this point in the history

  2. enable flash decoding

    @FSSRepo
    FSSRepo committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    f490812 View commit details
    Browse the repository at this point in the history

  3. optional flash-decoding

    @FSSRepo
    FSSRepo committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    eecf7ee View commit details
    Browse the repository at this point in the history

Commits on Mar 8, 2024

  1. fix bug + debug prints

    @FSSRepo
    FSSRepo committed Mar 8, 2024
    Configuration menu
    Copy the full SHA
    be9ecd6 View commit details
    Browse the repository at this point in the history

  2. add more debug mods

    @FSSRepo
    FSSRepo committed Mar 8, 2024
    Configuration menu
    Copy the full SHA
    82374d0 View commit details
    Browse the repository at this point in the history

Commits on Mar 9, 2024

  1. fix mixtral models - flash decoding

    @FSSRepo
    FSSRepo committed Mar 9, 2024
    Configuration menu
    Copy the full SHA
    7b979d1 View commit details
    Browse the repository at this point in the history

  2. update test

    @FSSRepo
    FSSRepo committed Mar 9, 2024
    Configuration menu
    Copy the full SHA
    653b257 View commit details
    Browse the repository at this point in the history

Commits on Mar 14, 2024

  1. flash decoding load tile data in sram

    @FSSRepo
    FSSRepo committed Mar 14, 2024
    Configuration menu
    Copy the full SHA
    9d3b57e View commit details
    Browse the repository at this point in the history

Commits on Mar 23, 2024

  1. flash original

    @FSSRepo
    FSSRepo committed Mar 23, 2024
    Configuration menu
    Copy the full SHA
    7c28e0f View commit details
    Browse the repository at this point in the history

Commits on Mar 24, 2024

  1. fix linux library dir

    @FSSRepo
    FSSRepo committed Mar 24, 2024
    Configuration menu
    Copy the full SHA
    0a13dfe View commit details
    Browse the repository at this point in the history

  2. fix block size conversion

    @FSSRepo
    FSSRepo committed Mar 24, 2024
    Configuration menu
    Copy the full SHA
    19775b0 View commit details
    Browse the repository at this point in the history