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

[New Feature][Habana-Main] speculative_decoding HPU support #375

Open
wants to merge 10 commits into
base: habana_main
Choose a base branch
from
Open

[New Feature][Habana-Main] speculative_decoding HPU support #375

wants to merge 10 commits into from
+198 −44

Commits on Nov 6, 2024

  1. remove speculative_decoding hardcode to Cuda and add worker selector 

    There is one hardcode to HPUWorker, need to remove

Signed-off-by: Chendi.Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    84622c5 View commit details
    Browse the repository at this point in the history

  2. Review comments based fixings 

    Signed-off-by: Chendi Xue <[email protected]>
Signed-off-by: Chendi Xue <[email protected]>
    @xuechendi
    Chendi Xue authored and xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    6f734f5 View commit details
    Browse the repository at this point in the history

  3. Use platform to select base worker for MultiStepWorker 

    Signed-off-by: Chendi Xue <[email protected]>
    @xuechendi
    Chendi Xue authored and xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    8fa5c82 View commit details
    Browse the repository at this point in the history

  4. resolve issue after rebase 

    Signed-off-by: Chendi Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    b0bf82e View commit details
    Browse the repository at this point in the history

  5. Fix format issue reported by yapf, ruff, isort, mypy 

    Signed-off-by: Chendi Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    cf1f4d3 View commit details
    Browse the repository at this point in the history

  6. update format based on yapf detection 

    Signed-off-by: Chendi.Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    14f70a7 View commit details
    Browse the repository at this point in the history

  7. fix per comments 

    Signed-off-by: Chendi.Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    972c4ee View commit details
    Browse the repository at this point in the history

  8. Fix both yapf and ruff detected issue 

    Signed-off-by: Chendi.Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    8a33969 View commit details
    Browse the repository at this point in the history

  9. rebase and fix format issue 

    Signed-off-by: Chendi Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    af938b8 View commit details
    Browse the repository at this point in the history

  10. Fix after rebase 

    Signed-off-by: Chendi Xue <[email protected]>
    @xuechendi
    xuechendi committed Nov 6, 2024
    Configuration menu
    Copy the full SHA
    20a2e67 View commit details
    Browse the repository at this point in the history