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

Separate attention backends #3005

Merged
merged 44 commits into from
Mar 7, 2024
Merged

Separate attention backends #3005

merged 44 commits into from
Mar 7, 2024

Commits on Feb 23, 2024

  1. Add attention_backends

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    a40b2c9 View commit details
    Browse the repository at this point in the history

  2. Move

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    6b6f7c7 View commit details
    Browse the repository at this point in the history

  3. Remove if

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    f2b888c View commit details
    Browse the repository at this point in the history

  4. Remove if

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    7f4422c View commit details
    Browse the repository at this point in the history

  5. Attention

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    1d9dc99 View commit details
    Browse the repository at this point in the history

  6. Minor

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    534d0f8 View commit details
    Browse the repository at this point in the history

  7. Minor

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    404022a View commit details
    Browse the repository at this point in the history

  8. Rename

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    194df2f View commit details
    Browse the repository at this point in the history

  9. Add flash-attn

    @WoosukKwon
    WoosukKwon committed Feb 23, 2024
    Configuration menu
    Copy the full SHA
    a6910ea View commit details
    Browse the repository at this point in the history

Commits on Feb 27, 2024

  1. Address review

    @WoosukKwon
    WoosukKwon committed Feb 27, 2024
    Configuration menu
    Copy the full SHA
    346b1b7 View commit details
    Browse the repository at this point in the history

Commits on Feb 28, 2024

  1. Merge branch 'main' into refactor-attn

    @WoosukKwon
    WoosukKwon committed Feb 28, 2024
    Configuration menu
    Copy the full SHA
    05579fa View commit details
    Browse the repository at this point in the history

Commits on Feb 29, 2024

  1. Move

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    da115dd View commit details
    Browse the repository at this point in the history

  2. Move

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    19ecd4d View commit details
    Browse the repository at this point in the history

  3. Minor

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    5b8e8c7 View commit details
    Browse the repository at this point in the history

  4. Rename

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    ef8ace1 View commit details
    Browse the repository at this point in the history

  5. Fix attention

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    6490fb4 View commit details
    Browse the repository at this point in the history

  6. Minor

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    3baebac View commit details
    Browse the repository at this point in the history

  7. Minor

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    6a81692 View commit details
    Browse the repository at this point in the history

  8. Minor

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    963a2c7 View commit details
    Browse the repository at this point in the history

  9. Add comment

    @WoosukKwon
    WoosukKwon committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    38baed7 View commit details
    Browse the repository at this point in the history

Commits on Mar 5, 2024

  1. Merge branch 'main' into refactor-attn

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    f97fc52 View commit details
    Browse the repository at this point in the history

  2. Attention backends -> Attention

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    89069b8 View commit details
    Browse the repository at this point in the history

  3. Move

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    9ba068a View commit details
    Browse the repository at this point in the history

  4. Move

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    677ad69 View commit details
    Browse the repository at this point in the history

  5. Minor

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    f5c7b07 View commit details
    Browse the repository at this point in the history

  6. Ops

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    4a80dd0 View commit details
    Browse the repository at this point in the history

  7. Minor

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    1319fc9 View commit details
    Browse the repository at this point in the history

  8. Import Attention

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    281c5d5 View commit details
    Browse the repository at this point in the history

  9. Minor

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    2f32381 View commit details
    Browse the repository at this point in the history

  10. Update models

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    c68fe7e View commit details
    Browse the repository at this point in the history

  11. forward -> forward_decode

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    f65f65d View commit details
    Browse the repository at this point in the history

  12. Add packaging to requirements

    @WoosukKwon
    WoosukKwon committed Mar 5, 2024
    Configuration menu
    Copy the full SHA
    45d02a1 View commit details
    Browse the repository at this point in the history

Commits on Mar 6, 2024

  1. Merge branch 'main' into refactor-attn

    @WoosukKwon
    WoosukKwon committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    8e5ca7e View commit details
    Browse the repository at this point in the history

  2. Remove FlashAttention from requirements

    @WoosukKwon
    WoosukKwon committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    8333223 View commit details
    Browse the repository at this point in the history

  3. Add FlashInfer wheels to vLLM

    @WoosukKwon
    WoosukKwon committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    ed1ab56 View commit details
    Browse the repository at this point in the history

  4. Minor

    @WoosukKwon
    WoosukKwon committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    73aedbd View commit details
    Browse the repository at this point in the history

  5. maybe fix packaging

    @WoosukKwon
    WoosukKwon committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    0214afd View commit details
    Browse the repository at this point in the history

  6. Add gitignore

    @WoosukKwon
    WoosukKwon committed Mar 6, 2024
    Configuration menu
    Copy the full SHA
    12ea60d View commit details
    Browse the repository at this point in the history

Commits on Mar 7, 2024

  1. Revert

    @WoosukKwon
    WoosukKwon committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    b460c21 View commit details
    Browse the repository at this point in the history

  2. revert

    @WoosukKwon
    WoosukKwon committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    4ffa89f View commit details
    Browse the repository at this point in the history

  3. Copy after build

    @WoosukKwon
    WoosukKwon committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    6ba0e70 View commit details
    Browse the repository at this point in the history

  4. Binary distribution

    @WoosukKwon
    WoosukKwon committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    974db99 View commit details
    Browse the repository at this point in the history

  5. yapf

    @WoosukKwon
    WoosukKwon committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    f72560c View commit details
    Browse the repository at this point in the history

  6. Fix a bug for FP32

    @WoosukKwon
    WoosukKwon committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    0b8ac9e View commit details
    Browse the repository at this point in the history