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

feat: engine caching #2995

Merged
merged 14 commits into from
Aug 29, 2024
Merged

feat: engine caching #2995

merged 14 commits into from
Aug 29, 2024

Commits on Aug 29, 2024

  1. feat: engine caching 

    revert backend changes

update dynamo path

add save_engine_cache and load_engine_cache args

support customizing engine cache class

refactor and add LRU to clear cache

fix bug
    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    1d60e53 View commit details
    Browse the repository at this point in the history

  2. rebase

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    f3d1084 View commit details
    Browse the repository at this point in the history

  3. add comments

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    1e5b501 View commit details
    Browse the repository at this point in the history

  4. add bert example

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    bc0a8c0 View commit details
    Browse the repository at this point in the history

  5. support saving weight name map

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    79544e3 View commit details
    Browse the repository at this point in the history

  6. refactor

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    a7b7676 View commit details
    Browse the repository at this point in the history

  7. small fixes

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    64885de View commit details
    Browse the repository at this point in the history

  8. move refit into interpret_module_to_result

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    88d1a25 View commit details
    Browse the repository at this point in the history

  9. update refit usage

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    81eb7c5 View commit details
    Browse the repository at this point in the history

  10. force using slow refit, add unit tests

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    04bb63a View commit details
    Browse the repository at this point in the history

  11. fix issues from comments, add more unit tests

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    16315dd View commit details
    Browse the repository at this point in the history

  12. fix CI errors

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    f3e4234 View commit details
    Browse the repository at this point in the history

  13. fix CI errors

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    42d18ac View commit details
    Browse the repository at this point in the history

  14. fix refit issue for torch.compile

    @zewenli98
    zewenli98 committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    fc525e6 View commit details
    Browse the repository at this point in the history