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

[NNAdapter][QualcommQNN] Supports ERNIE nano fully quantized model #9618

Merged
merged 4 commits into from
Nov 7, 2022
Merged

[NNAdapter][QualcommQNN] Supports ERNIE nano fully quantized model #9618

merged 4 commits into from
Nov 7, 2022

Commits on Oct 31, 2022

  1. [NNAdapter][QualcommQNN] Fix matmul+add+softmax for ernie int8 model 

    Change-Id: I49034a6a432717b917bd1eb2993e5e6b33d8fe5c
    @hong19860320
    hong19860320 committed Oct 31, 2022
    Configuration menu
    Copy the full SHA
    942c97c View commit details
    Browse the repository at this point in the history

Commits on Nov 3, 2022

  1. fix int8 

    Change-Id: Ia9dca6e3a504a5e6f1ab877a4c3c10b5edc795c7
    @hong19860320
    hong19860320 committed Nov 3, 2022
    Configuration menu
    Copy the full SHA
    849fc2f View commit details
    Browse the repository at this point in the history

Commits on Nov 6, 2022

  1. Dump the variables without outscale test=huawei_ascend_npu 

    Change-Id: If4cb513e3b55095107c6c1c302b2696475ad9916
    @hong19860320
    hong19860320 committed Nov 6, 2022
    Configuration menu
    Copy the full SHA
    6d1caab View commit details
    Browse the repository at this point in the history

  2. Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle-Lite … 

    …into hongming/fix_ernie_int8_qnn

test=huawei_ascend_npu
    @hong19860320
    hong19860320 committed Nov 6, 2022
    Configuration menu
    Copy the full SHA
    73d475b View commit details
    Browse the repository at this point in the history