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

[Kernel][Model] logits_soft_cap for Gemma2 with flashinfer #6051

Merged
merged 15 commits into from
Jul 4, 2024
Merged

[Kernel][Model] logits_soft_cap for Gemma2 with flashinfer #6051

merged 15 commits into from
Jul 4, 2024

Commits on Jul 1, 2024

  1. logits_soft_cap for gemma2 in flashinfer

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    c7ddd18 View commit details
    Browse the repository at this point in the history

  2. separate tests

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    ceb7a16 View commit details
    Browse the repository at this point in the history

  3. minor

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    afa1ef3 View commit details
    Browse the repository at this point in the history

  4. format

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    6426e9b View commit details
    Browse the repository at this point in the history

  5. format

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    8423d03 View commit details
    Browse the repository at this point in the history

Commits on Jul 2, 2024

  1. add flashinfer unit test, update error message

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    54f8548 View commit details
    Browse the repository at this point in the history

  2. format

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    c0f298b View commit details
    Browse the repository at this point in the history

  3. Update .buildkite/test-pipeline.yaml 

    Co-authored-by: Simon Mo <simon.mo@hey.com>
    @LiuXiaoxuanPKU @simon-mo
    LiuXiaoxuanPKU and simon-mo committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    d248cef View commit details
    Browse the repository at this point in the history

Commits on Jul 3, 2024

  1. fix

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    0947961 View commit details
    Browse the repository at this point in the history

Commits on Jul 4, 2024

  1. remove warning

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    0cc481c View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' of github.com:LiuXiaoxuanPKU/vllm

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    06b1a4f View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' into flashinfer-logit-soft-cap

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    1f266c6 View commit details
    Browse the repository at this point in the history

  4. fix merge bug

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    cf02682 View commit details
    Browse the repository at this point in the history

  5. format

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    8e4d1d3 View commit details
    Browse the repository at this point in the history

  6. remove model test since unit tests already convered and unblock release

    @LiuXiaoxuanPKU
    LiuXiaoxuanPKU committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    5257015 View commit details
    Browse the repository at this point in the history