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

FP8 ONNX导出问题 #266

Open
wants to merge 32 commits into
base: main
Choose a base branch
from
Open

FP8 ONNX导出问题 #266

wants to merge 32 commits into from

Commits on Oct 9, 2022

  1. test

    @wangxc2006
    wangxc2006 committed Oct 9, 2022
    Configuration menu
    Copy the full SHA
    c9e8504 View commit details
    Browse the repository at this point in the history

  2. support sophgo_tpu backend,initial ver

    @wangxc2006
    wangxc2006 committed Oct 9, 2022
    Configuration menu
    Copy the full SHA
    0491be5 View commit details
    Browse the repository at this point in the history

Commits on Nov 3, 2022

  1. update, fix some bug

    @wangxc2006
    wangxc2006 committed Nov 3, 2022
    Configuration menu
    Copy the full SHA
    ef3f30e View commit details
    Browse the repository at this point in the history

  2. add deconv and refine SophgoTpuQuantizer

    @wangxc2006
    wangxc2006 committed Nov 3, 2022
    Configuration menu
    Copy the full SHA
    96683b6 View commit details
    Browse the repository at this point in the history

Commits on Nov 15, 2022

  1. add some verfiy code

    @wangxc2006
    wangxc2006 committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    e612cfd View commit details
    Browse the repository at this point in the history

Commits on Dec 1, 2022

  1. for qat int8 release

    @wangxc2006
    wangxc2006 committed Dec 1, 2022
    Configuration menu
    Copy the full SHA
    99775c4 View commit details
    Browse the repository at this point in the history

Commits on Dec 5, 2022

  1. for qat int8 release

    @wangxc2006
    wangxc2006 committed Dec 5, 2022
    Configuration menu
    Copy the full SHA
    252ede6 View commit details
    Browse the repository at this point in the history

Commits on Feb 27, 2023

  1. fix linear+bn bug

    @wangxc2006
    wangxc2006 committed Feb 27, 2023
    Configuration menu
    Copy the full SHA
    cfddb1d View commit details
    Browse the repository at this point in the history

Commits on Apr 12, 2023

  1. add int4&int8 mix prec func and infer net output shape in xxx_mqmoble… 

    …_deploy_model.onnx
    @wangxc2006
    wangxc2006 committed Apr 12, 2023
    Configuration menu
    Copy the full SHA
    21f39c0 View commit details
    Browse the repository at this point in the history

  2. fix int8 bug in int4 version

    @wangxc2006
    wangxc2006 committed Apr 12, 2023
    Configuration menu
    Copy the full SHA
    232ca1f View commit details
    Browse the repository at this point in the history

Commits on Jun 21, 2023

  1. fix sub/abs op no fake quant node

    @wangxc2006
    wangxc2006 committed Jun 21, 2023
    Configuration menu
    Copy the full SHA
    1d09bc4 View commit details
    Browse the repository at this point in the history

Commits on Aug 2, 2023

  1. add some class and func to adapt to torch1.10_cpu and torch2.0.1_cpu

    @zhengjin-xu11
    zhengjin-xu11 committed Aug 2, 2023
    Configuration menu
    Copy the full SHA
    1f43b9d View commit details
    Browse the repository at this point in the history

Commits on Aug 14, 2023

  1. commit message here

    @shee-gao
    shee-gao committed Aug 14, 2023
    Configuration menu
    Copy the full SHA
    47c3cde View commit details
    Browse the repository at this point in the history

Commits on Aug 15, 2023

  1. commit message here

    @shee-gao
    shee-gao committed Aug 15, 2023
    Configuration menu
    Copy the full SHA
    2612562 View commit details
    Browse the repository at this point in the history

Commits on Aug 29, 2023

  1. qat gpt2

    @shee-gao
    shee-gao committed Aug 29, 2023
    Configuration menu
    Copy the full SHA
    4642917 View commit details
    Browse the repository at this point in the history

Commits on Aug 30, 2023

  1. 添加了FP8 fakequant以及修改了config以及prepare_by_platform中的一些问题”

    @tjthereal
    tjthereal committed Aug 30, 2023
    Configuration menu
    Copy the full SHA
    99f2a16 View commit details
    Browse the repository at this point in the history

  2. QAT example

    @shee-gao
    shee-gao committed Aug 30, 2023
    Configuration menu
    Copy the full SHA
    e57a418 View commit details
    Browse the repository at this point in the history

Commits on Aug 31, 2023

  1. [Feature] NLP trace support and example

    @shee-gao
    shee-gao committed Aug 31, 2023
    Configuration menu
    Copy the full SHA
    459ed0b View commit details
    Browse the repository at this point in the history

Commits on Sep 5, 2023

  1. hide STOCHASTIC

    @tjthereal
    tjthereal committed Sep 5, 2023
    Configuration menu
    Copy the full SHA
    a6b2c12 View commit details
    Browse the repository at this point in the history

Commits on Sep 11, 2023

  1. Add GPTQ

    @yz-zhang-sg @WhoIsYu
    yz-zhang-sg authored and WhoIsYu committed Sep 11, 2023
    Configuration menu
    Copy the full SHA
    505b832 View commit details
    Browse the repository at this point in the history

  2. Update gptq.py 

    Update GPTQFakeQuantize
    @yz-zhang-sg @WhoIsYu
    yz-zhang-sg authored and WhoIsYu committed Sep 11, 2023
    Configuration menu
    Copy the full SHA
    96caec1 View commit details
    Browse the repository at this point in the history

  3. Add bert-base-uncased-mrpc GPTQ version

    @yz-zhang-sg @WhoIsYu
    yz-zhang-sg authored and WhoIsYu committed Sep 11, 2023
    Configuration menu
    Copy the full SHA
    de5a1c1 View commit details
    Browse the repository at this point in the history

  4. Fixed two devices problem

    @yz-zhang-sg @WhoIsYu
    yz-zhang-sg authored and WhoIsYu committed Sep 11, 2023
    Configuration menu
    Copy the full SHA
    892331d View commit details
    Browse the repository at this point in the history

  5. Update gptq.py

    @yz-zhang-sg @WhoIsYu
    yz-zhang-sg authored and WhoIsYu committed Sep 11, 2023
    Configuration menu
    Copy the full SHA
    73fc14e View commit details
    Browse the repository at this point in the history

  6. gptq use academic backend

    @yz-zhang-sg @WhoIsYu
    yz-zhang-sg authored and WhoIsYu committed Sep 11, 2023
    Configuration menu
    Copy the full SHA
    02c248f View commit details
    Browse the repository at this point in the history

  7. fix model insert & delete info | fix deploy

    @yz-zhang-sg @WhoIsYu
    yz-zhang-sg authored and WhoIsYu committed Sep 11, 2023
    Configuration menu
    Copy the full SHA
    dc22db9 View commit details
    Browse the repository at this point in the history

Commits on Sep 12, 2023

  1. nlp deploy

    @shee-gao
    shee-gao committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    1530d26 View commit details
    Browse the repository at this point in the history

  2. 1.Correcting the method for registering operators in MQBench. 

    2.Modify the method of exporting Onnx and add checks for the exported Onnx files.

3.Fix the PTQ bug under sophgo_tpu backend.
    @zhengjin-xu11
    zhengjin-xu11 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    5c6e623 View commit details
    Browse the repository at this point in the history

  3. Complete merge

    @shee-gao
    shee-gao committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    38a0c54 View commit details
    Browse the repository at this point in the history

  4. conflict fixed

    @zhengjin-xu11
    zhengjin-xu11 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    195b522 View commit details
    Browse the repository at this point in the history

Commits on Sep 14, 2023

  1. add fast test before push

    @zhengjin-xu11
    zhengjin-xu11 committed Sep 14, 2023
    Configuration menu
    Copy the full SHA
    d489ab7 View commit details
    Browse the repository at this point in the history

  2. FP8 ONNX problem

    @tjthereal
    tjthereal committed Sep 14, 2023
    Configuration menu
    Copy the full SHA
    4290bd7 View commit details
    Browse the repository at this point in the history