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 IPEX-XPU support for Llama2 model Inference #703

Draft
wants to merge 38 commits into
base: main
Choose a base branch
from
Draft

add IPEX-XPU support for Llama2 model Inference #703

wants to merge 38 commits into from

Commits on May 8, 2024

  1. add xpu patch to optimum intel (huggingface#7) 

    * add xpu patch to optimum intel

* simple path for xpu inference
    @ganyi1996ppo @faaany
    ganyi1996ppo authored and faaany committed May 8, 2024
    Configuration menu
    Copy the full SHA
    5c4d13f View commit details
    Browse the repository at this point in the history

  2. can run but precision error

    @jiqing-feng @faaany
    jiqing-feng authored and faaany committed May 8, 2024
    Configuration menu
    Copy the full SHA
    b1d6989 View commit details
    Browse the repository at this point in the history

  3. optimize optimum

    @ganyi1996ppo @faaany
    ganyi1996ppo authored and faaany committed May 8, 2024
    Configuration menu
    Copy the full SHA
    f2de914 View commit details
    Browse the repository at this point in the history

  4. further optimize

    @ganyi1996ppo @faaany
    ganyi1996ppo authored and faaany committed May 8, 2024
    Configuration menu
    Copy the full SHA
    9295457 View commit details
    Browse the repository at this point in the history

  5. finalize

    @faaany
    faaany committed May 8, 2024
    Configuration menu
    Copy the full SHA
    c55216a View commit details
    Browse the repository at this point in the history

Commits on May 9, 2024

  1. fix version

    @faaany
    faaany committed May 9, 2024
    Configuration menu
    Copy the full SHA
    5b3b72d View commit details
    Browse the repository at this point in the history

Commits on May 11, 2024

  1. fix ipex version check

    @faaany
    faaany committed May 11, 2024
    Configuration menu
    Copy the full SHA
    4897144 View commit details
    Browse the repository at this point in the history

Commits on May 23, 2024

  1. ipex 2.3 released

    @jiqing-feng
    jiqing-feng committed May 23, 2024
    Configuration menu
    Copy the full SHA
    5351f4a View commit details
    Browse the repository at this point in the history

Commits on May 24, 2024

  1. change versions

    @faaany
    faaany committed May 24, 2024
    Configuration menu
    Copy the full SHA
    6289b57 View commit details
    Browse the repository at this point in the history

  2. debug beam search

    @faaany
    faaany committed May 24, 2024
    Configuration menu
    Copy the full SHA
    3824300 View commit details
    Browse the repository at this point in the history

  3. remove reference elimination

    @faaany
    faaany committed May 24, 2024
    Configuration menu
    Copy the full SHA
    872a3eb View commit details
    Browse the repository at this point in the history

Commits on May 25, 2024

  1. refactor IPEXLlamaAttention

    @faaany
    faaany committed May 25, 2024
    Configuration menu
    Copy the full SHA
    d1d0ca0 View commit details
    Browse the repository at this point in the history

Commits on May 26, 2024

  1. Merge branch 'ipex-cpu' into ipex-xpu

    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    3b8900d View commit details
    Browse the repository at this point in the history

  2. Merge branch 'huggingface:main' into ipex-xpu

    @faaany
    faaany authored May 26, 2024
    Configuration menu
    Copy the full SHA
    815d238 View commit details
    Browse the repository at this point in the history

  3. add xpu port

    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    89e10d6 View commit details
    Browse the repository at this point in the history

  4. Fix llama and gemma modeling patching for openvino export (huggingfac… 

    …e#714)

* Fix compatibility for transformers v4.41.0 llama and gemma modeling patching

* fix for dev transformers version

* update setup
    @echarlaix @faaany
    echarlaix authored and faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    9acaba4 View commit details
    Browse the repository at this point in the history

  5. Fix nncf quantization for decoder models (huggingface#727) 

    * Fix nncf quantization for decoder models

* add test

* update op quant op

* remove deprecated warning

* update expected quantized

* enable stateful

* style
    @echarlaix @faaany
    echarlaix authored and faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    2f4909c View commit details
    Browse the repository at this point in the history

  6. Merge branch 'ipex-xpu' of https://github.com/faaany/optimum-intel in… 

    …to ipex-xpu
    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    17d02d3 View commit details
    Browse the repository at this point in the history

  7. remove

    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    f186ce7 View commit details
    Browse the repository at this point in the history

  8. fix version

    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    1ff78b2 View commit details
    Browse the repository at this point in the history

  9. bug fix

    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    ff7f785 View commit details
    Browse the repository at this point in the history

  10. change module

    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    e3dac89 View commit details
    Browse the repository at this point in the history

  11. improve device

    @faaany
    faaany committed May 26, 2024
    Configuration menu
    Copy the full SHA
    8725f49 View commit details
    Browse the repository at this point in the history

Commits on May 27, 2024

  1. remove

    @faaany
    faaany committed May 27, 2024
    Configuration menu
    Copy the full SHA
    57cfe11 View commit details
    Browse the repository at this point in the history

  2. simplfy rmsnorm

    @faaany
    faaany committed May 27, 2024
    Configuration menu
    Copy the full SHA
    ee78f95 View commit details
    Browse the repository at this point in the history

  3. Merge branch 'ipex-xpu' of https://github.com/faaany/optimum-intel in… 

    …to ipex-xpu
    @faaany
    faaany committed May 27, 2024
    Configuration menu
    Copy the full SHA
    a930f31 View commit details
    Browse the repository at this point in the history

  4. style

    @faaany
    faaany committed May 27, 2024
    Configuration menu
    Copy the full SHA
    6098943 View commit details
    Browse the repository at this point in the history

Commits on Jun 7, 2024

  1. fix group attention

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    e0fb06e View commit details
    Browse the repository at this point in the history

  2. fix weight shape

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    aa8d395 View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' into ipex-xpu

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    0a56b19 View commit details
    Browse the repository at this point in the history

  4. fix rebase bug

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    548d83f View commit details
    Browse the repository at this point in the history

  5. revert openvino

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    68187e5 View commit details
    Browse the repository at this point in the history

  6. revert openvino

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    efedca4 View commit details
    Browse the repository at this point in the history

  7. remove duplicates

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    bd03552 View commit details
    Browse the repository at this point in the history

  8. use the correct black

    @faaany
    faaany committed Jun 7, 2024
    Configuration menu
    Copy the full SHA
    0d3930a View commit details
    Browse the repository at this point in the history

Commits on Sep 6, 2024

  1. Merge branch 'main' into ipex-xpu

    @faaany
    faaany authored Sep 6, 2024
    Configuration menu
    Copy the full SHA
    b4ba6d0 View commit details
    Browse the repository at this point in the history

Commits on Sep 10, 2024

  1. fix merge conflict 

    Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
    @kaixuanliu
    kaixuanliu committed Sep 10, 2024
    Configuration menu
    Copy the full SHA
    1fd464b View commit details
    Browse the repository at this point in the history

  2. Merge pull request #1 from kaixuanliu/ipex-xpu 

    fix merge conflict
    @kaixuanliu
    kaixuanliu authored Sep 10, 2024
    Configuration menu
    Copy the full SHA
    6a52fdf View commit details
    Browse the repository at this point in the history