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

Feature/npu #5310

Merged
merged 10 commits into from
Jan 29, 2024
Merged

Feature/npu #5310

merged 10 commits into from
Jan 29, 2024

Commits on Nov 30, 2023

  1. [accelerator] init the accelerator module (#5129) 

    * [accelerator] init the accelerator module

* polish code

* polish code

* polish code

* polish code
    @FrankLeeeee
    FrankLeeeee authored Nov 30, 2023
    Configuration menu
    Copy the full SHA
    f4e72c9 View commit details
    Browse the repository at this point in the history

  2. [npu] support triangle attention for llama (#5130) 

    * update fused attn

* update spda

* tri attn

* update triangle

* import

* fix

* fix
    @oahzxl
    oahzxl authored Nov 30, 2023
    Configuration menu
    Copy the full SHA
    d6df19b View commit details
    Browse the repository at this point in the history

Commits on Jan 8, 2024

  1. [npu] use extension for op builder (#5172) 

    * update extension

* update cpu adam

* update is

* add doc for cpu adam

* update kernel

* update commit

* update flash

* update memory efficient

* update flash attn

* update flash attention loader

* update api

* fix

* update doc

* update example time limit

* reverse change

* fix doc

* remove useless kernel

* fix

* not use warning

* update

* update
    @oahzxl
    oahzxl authored Jan 8, 2024
    Configuration menu
    Copy the full SHA
    dd2c28a View commit details
    Browse the repository at this point in the history

Commits on Jan 9, 2024

  1. [npu] change device to accelerator api (#5239) 

    * update accelerator

* fix timer

* fix amp

* update

* fix

* update bug

* add error raise

* fix autocast

* fix set device

* remove doc accelerator

* update doc

* update doc

* update doc

* use nullcontext

* update cpu

* update null context

* change time limit for example

* udpate

* update

* update

* update

* [npu] polish accelerator code

---------

Co-authored-by: Xuanlei Zhao <[email protected]>
Co-authored-by: zxl <[email protected]>
    @ver217 @oahzxl
    3 people authored Jan 9, 2024
    Configuration menu
    Copy the full SHA
    d202cc2 View commit details
    Browse the repository at this point in the history

  2. [hotfix] removed unused flag (#5242)

    @FrankLeeeee
    FrankLeeeee authored Jan 9, 2024
    Configuration menu
    Copy the full SHA
    9102d65 View commit details
    Browse the repository at this point in the history

Commits on Jan 18, 2024

  1. Merge branch 'main' into sync/npu

    @ver217
    ver217 committed Jan 18, 2024
    Configuration menu
    Copy the full SHA
    1484693 View commit details
    Browse the repository at this point in the history

  2. Merge pull request #5278 from ver217/sync/npu 

    [sync] sync npu branch with main
    @FrankLeeeee
    FrankLeeeee authored Jan 18, 2024
    Configuration menu
    Copy the full SHA
    d66e698 View commit details
    Browse the repository at this point in the history

Commits on Jan 22, 2024

  1. [hotfix] fix 3d plugin test (#5292)

    @ver217
    ver217 authored Jan 22, 2024
    Configuration menu
    Copy the full SHA
    d7f8db8 View commit details
    Browse the repository at this point in the history

Commits on Jan 25, 2024

  1. [feat] refactored extension module (#5298) 

    * [feat] refactored extension module

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish
    @FrankLeeeee
    FrankLeeeee authored Jan 25, 2024
    Configuration menu
    Copy the full SHA
    7cfed5f View commit details
    Browse the repository at this point in the history

Commits on Jan 29, 2024

  1. [workflow] updated CI image (#5318)

    @FrankLeeeee
    FrankLeeeee authored Jan 29, 2024
    Configuration menu
    Copy the full SHA
    73f4dc5 View commit details
    Browse the repository at this point in the history