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

SRT refactor #844

Closed
wants to merge 35 commits into from
Closed

SRT refactor #844

wants to merge 35 commits into from

Commits on Jul 31, 2024

  1. rename

    @hnyls2002
    hnyls2002 committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    95db0dc View commit details
    Browse the repository at this point in the history

  2. move ForwardMode into forward_batch

    @hnyls2002
    hnyls2002 committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    a437c18 View commit details
    Browse the repository at this point in the history

  3. rename

    @hnyls2002
    hnyls2002 committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    c21d338 View commit details
    Browse the repository at this point in the history

  4. move input_metadata

    @hnyls2002
    hnyls2002 committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    912e484 View commit details
    Browse the repository at this point in the history

  5. update init_triton

    @hnyls2002
    hnyls2002 committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    2a968c4 View commit details
    Browse the repository at this point in the history

  6. fix typo

    @hnyls2002
    hnyls2002 committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    8cd2d21 View commit details
    Browse the repository at this point in the history

  7. organize init_flashinfer: to clean up inpute_metadata.create

    @hnyls2002
    hnyls2002 committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    bffd828 View commit details
    Browse the repository at this point in the history

Commits on Aug 2, 2024

  1. align with main: test CI

    @hnyls2002
    hnyls2002 committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    d9ecd7a View commit details
    Browse the repository at this point in the history

  2. update

    @hnyls2002
    hnyls2002 committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    9b58945 View commit details
    Browse the repository at this point in the history

  3. update

    @hnyls2002
    hnyls2002 committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    f4d8364 View commit details
    Browse the repository at this point in the history

  4. remove req_pool_indices.cpu

    @hnyls2002
    hnyls2002 committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    5256a52 View commit details
    Browse the repository at this point in the history

  5. req_pool slots: gpu -> cpu

    @hnyls2002
    hnyls2002 committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    4b2dc62 View commit details
    Browse the repository at this point in the history

Commits on Aug 3, 2024

  1. allow for using existed req_pool_idx

    @hnyls2002
    hnyls2002 committed Aug 3, 2024
    Configuration menu
    Copy the full SHA
    cc8e5e4 View commit details
    Browse the repository at this point in the history

  2. clear logic for batch filter/merge

    @hnyls2002
    hnyls2002 committed Aug 3, 2024
    Configuration menu
    Copy the full SHA
    1a3db54 View commit details
    Browse the repository at this point in the history

  3. move adjust input len

    @hnyls2002
    hnyls2002 committed Aug 3, 2024
    Configuration menu
    Copy the full SHA
    65c5bb1 View commit details
    Browse the repository at this point in the history

Commits on Aug 4, 2024

  1. prefill adder

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    571bf62 View commit details
    Browse the repository at this point in the history

  2. fix conflicts

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    7f7d383 View commit details
    Browse the repository at this point in the history

  3. clean up

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    9b3483f View commit details
    Browse the repository at this point in the history

  4. clarify cache operations

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    9751b66 View commit details
    Browse the repository at this point in the history

  5. revert "allow for using existed req_pool_idx"

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    c3f9afd View commit details
    Browse the repository at this point in the history

  6. fix chunked prefill

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    721f964 View commit details
    Browse the repository at this point in the history

  7. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    a470115 View commit details
    Browse the repository at this point in the history

  8. clean chunked prefill logic

    @hnyls2002
    hnyls2002 committed Aug 4, 2024
    Configuration menu
    Copy the full SHA
    1f5219d View commit details
    Browse the repository at this point in the history

Commits on Aug 5, 2024

  1. create -> from batch

    @hnyls2002
    hnyls2002 committed Aug 5, 2024
    Configuration menu
    Copy the full SHA
    258eb2b View commit details
    Browse the repository at this point in the history

  2. rewrite inpute_metadata

    @hnyls2002
    hnyls2002 committed Aug 5, 2024
    Configuration menu
    Copy the full SHA
    e78dcb8 View commit details
    Browse the repository at this point in the history

  3. extend_lens_cpu && prefix_lens_cpu

    @hnyls2002
    hnyls2002 committed Aug 5, 2024
    Configuration menu
    Copy the full SHA
    3e67727 View commit details
    Browse the repository at this point in the history

  4. move multimodal infos

    @hnyls2002
    hnyls2002 committed Aug 5, 2024
    Configuration menu
    Copy the full SHA
    c164fb3 View commit details
    Browse the repository at this point in the history

  5. clear

    @hnyls2002
    hnyls2002 committed Aug 5, 2024
    Configuration menu
    Copy the full SHA
    dc50933 View commit details
    Browse the repository at this point in the history

Commits on Aug 7, 2024

  1. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    b48fe4c View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    626d92c View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    f4b6820 View commit details
    Browse the repository at this point in the history

  4. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    44406fe View commit details
    Browse the repository at this point in the history

  5. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    5846f73 View commit details
    Browse the repository at this point in the history

Commits on Aug 8, 2024

  1. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 8, 2024
    Configuration menu
    Copy the full SHA
    d1d5f15 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into shedule-batch

    @hnyls2002
    hnyls2002 committed Aug 8, 2024
    Configuration menu
    Copy the full SHA
    5b34ef9 View commit details
    Browse the repository at this point in the history