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] Enable 8-bit weights in Fused Marlin MoE #8032

Merged
merged 30 commits into from
Sep 16, 2024
Merged

[Kernel] Enable 8-bit weights in Fused Marlin MoE #8032

merged 30 commits into from
Sep 16, 2024

Commits on Aug 30, 2024

  1. Enable 8-bit weights in Fused Marlin MoE

    @ElizaWszola
    ElizaWszola committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    0abac6f View commit details
    Browse the repository at this point in the history

  2. fix rocm

    @ElizaWszola
    ElizaWszola committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    fdf69c2 View commit details
    Browse the repository at this point in the history

  3. bad paste

    @ElizaWszola
    ElizaWszola committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    4da163b View commit details
    Browse the repository at this point in the history

  4. add test case; fix imports for tests

    @dsikka
    dsikka committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    21d2337 View commit details
    Browse the repository at this point in the history

  5. Merge branch 'main' into marlin-moe-8-bit

    @dsikka
    dsikka authored Aug 30, 2024
    Configuration menu
    Copy the full SHA
    080ab23 View commit details
    Browse the repository at this point in the history

  6. fix to adapt custom_routin_function

    @dsikka
    dsikka committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    638777a View commit details
    Browse the repository at this point in the history

Commits on Sep 2, 2024

  1. Use select_experts to compute top_k tensors in fused moe

    @ElizaWszola
    ElizaWszola committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    bd4b84d View commit details
    Browse the repository at this point in the history

Commits on Sep 3, 2024

  1. bring back fused_moe_marlin -> fused_marlin_moe

    @ElizaWszola
    ElizaWszola committed Sep 3, 2024
    Configuration menu
    Copy the full SHA
    bef6b53 View commit details
    Browse the repository at this point in the history

Commits on Sep 4, 2024

  1. Merge branch 'main' into marlin-moe-8-bit

    @ElizaWszola
    ElizaWszola committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    befc52b View commit details
    Browse the repository at this point in the history

  2. remove large model

    @dsikka
    dsikka committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    b45594c View commit details
    Browse the repository at this point in the history

  3. Cleanup, comments

    @ElizaWszola
    ElizaWszola committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    effd2cd View commit details
    Browse the repository at this point in the history

  4. fix moe init

    @ElizaWszola
    ElizaWszola committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    52c3353 View commit details
    Browse the repository at this point in the history

  5. move larger models to an options larger test

    @dsikka
    dsikka committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    882fd9c View commit details
    Browse the repository at this point in the history

  6. add optional flag

    @dsikka
    dsikka committed Sep 4, 2024
    Configuration menu
    Copy the full SHA
    973d914 View commit details
    Browse the repository at this point in the history

Commits on Sep 5, 2024

  1. swap gpu

    @dsikka
    dsikka committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    72bc899 View commit details
    Browse the repository at this point in the history

  2. Temp disable part of moe tests to see what's breaking

    @ElizaWszola
    ElizaWszola committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    eea2bc3 View commit details
    Browse the repository at this point in the history

  3. Fixes to act_order, make unit tests more robust

    @ElizaWszola
    ElizaWszola committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    9c29dc2 View commit details
    Browse the repository at this point in the history

  4. try to narrow down cuda error

    @ElizaWszola
    ElizaWszola committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    6d04dcd View commit details
    Browse the repository at this point in the history

Commits on Sep 6, 2024

  1. Try different subset of test params

    @ElizaWszola
    ElizaWszola committed Sep 6, 2024
    Configuration menu
    Copy the full SHA
    83e7999 View commit details
    Browse the repository at this point in the history

  2. .

    @ElizaWszola
    ElizaWszola committed Sep 6, 2024
    Configuration menu
    Copy the full SHA
    6a42eaf View commit details
    Browse the repository at this point in the history

  3. .

    @ElizaWszola
    ElizaWszola committed Sep 6, 2024
    Configuration menu
    Copy the full SHA
    3288842 View commit details
    Browse the repository at this point in the history

Commits on Sep 10, 2024

  1. Merge branch 'main' into marlin-moe-8-bit

    @ElizaWszola
    ElizaWszola committed Sep 10, 2024
    Configuration menu
    Copy the full SHA
    61ef4ba View commit details
    Browse the repository at this point in the history

  2. fix and cleanup after merge

    @ElizaWszola
    ElizaWszola committed Sep 10, 2024
    Configuration menu
    Copy the full SHA
    667d23e View commit details
    Browse the repository at this point in the history

  3. cleanup

    @ElizaWszola
    ElizaWszola committed Sep 10, 2024
    Configuration menu
    Copy the full SHA
    b16838e View commit details
    Browse the repository at this point in the history

  4. validate cache for the kernel code

    @ElizaWszola
    ElizaWszola committed Sep 10, 2024
    Configuration menu
    Copy the full SHA
    e53abb9 View commit details
    Browse the repository at this point in the history

Commits on Sep 11, 2024

  1. cleanup commented out code

    @ElizaWszola
    ElizaWszola committed Sep 11, 2024
    Configuration menu
    Copy the full SHA
    2f82715 View commit details
    Browse the repository at this point in the history

Commits on Sep 13, 2024

  1. Merge branch 'main' into marlin-moe-8-bit

    @ElizaWszola
    ElizaWszola committed Sep 13, 2024
    Configuration menu
    Copy the full SHA
    f97b524 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into marlin-moe-8-bit

    @ElizaWszola
    ElizaWszola committed Sep 13, 2024
    Configuration menu
    Copy the full SHA
    771f693 View commit details
    Browse the repository at this point in the history

  3. fix type conversion

    @ElizaWszola
    ElizaWszola committed Sep 13, 2024
    Configuration menu
    Copy the full SHA
    aac7c20 View commit details
    Browse the repository at this point in the history

Commits on Sep 16, 2024

  1. Merge branch 'main' into marlin-moe-8-bit

    @ElizaWszola
    ElizaWszola committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    9d7caad View commit details
    Browse the repository at this point in the history