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

Marlin MoE integration #2

Closed
wants to merge 111 commits into from
Closed

Marlin MoE integration #2

wants to merge 111 commits into from

Commits on Aug 2, 2024

  1. Moving branch to a different repo

    @ElizaWszola
    ElizaWszola committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    5a2ab25 View commit details
    Browse the repository at this point in the history

  2. clean up the CPU code

    @ElizaWszola
    ElizaWszola committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    b39dba4 View commit details
    Browse the repository at this point in the history

  3. Fix build issues

    @ElizaWszola
    ElizaWszola committed Aug 2, 2024
    Configuration menu
    Copy the full SHA
    b0c4671 View commit details
    Browse the repository at this point in the history

Commits on Aug 7, 2024

  1. Refactoring for maintainability

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    e5c1a81 View commit details
    Browse the repository at this point in the history

  2. Fixing tests

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 7, 2024
    Configuration menu
    Copy the full SHA
    7da678e View commit details
    Browse the repository at this point in the history

Commits on Aug 8, 2024

  1. Addressing repacking comment

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 8, 2024
    Configuration menu
    Copy the full SHA
    641696b View commit details
    Browse the repository at this point in the history

  2. gptq -> marlin renaming

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 8, 2024
    Configuration menu
    Copy the full SHA
    3cef667 View commit details
    Browse the repository at this point in the history

  3. Undo formatting changes

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 8, 2024
    Configuration menu
    Copy the full SHA
    a6710af View commit details
    Browse the repository at this point in the history

  4. Final formatting change

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 8, 2024
    Configuration menu
    Copy the full SHA
    e29107f View commit details
    Browse the repository at this point in the history

Commits on Aug 12, 2024

  1. Switching to mixtral file for quantized mixtral

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    099d61e View commit details
    Browse the repository at this point in the history

  2. Bug fixes

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    bdf6bdc View commit details
    Browse the repository at this point in the history

  3. is quantized change

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    19c5c59 View commit details
    Browse the repository at this point in the history

  4. debug stat

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    3b7cc60 View commit details
    Browse the repository at this point in the history

  5. replace wiehgt name with param name

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    d2c4754 View commit details
    Browse the repository at this point in the history

  6. typo

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    f579cb2 View commit details
    Browse the repository at this point in the history

  7. debug

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    79394eb View commit details
    Browse the repository at this point in the history

  8. more debug

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    ec75f4e View commit details
    Browse the repository at this point in the history

  9. only relevant logging

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    91ca970 View commit details
    Browse the repository at this point in the history

  10. log

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    1b9d5bb View commit details
    Browse the repository at this point in the history

  11. log

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    ec06719 View commit details
    Browse the repository at this point in the history

  12. removing qzero weights

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    71d82e1 View commit details
    Browse the repository at this point in the history

  13. Qzeors in expert mapping

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    d3465d0 View commit details
    Browse the repository at this point in the history

  14. Debug

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    226ee26 View commit details
    Browse the repository at this point in the history

  15. Load qzero

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    21d7d27 View commit details
    Browse the repository at this point in the history

  16. rm 2x

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    2dabb4b View commit details
    Browse the repository at this point in the history

  17. Mapping for scales

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    6366976 View commit details
    Browse the repository at this point in the history

  18. rm logging

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    d63c096 View commit details
    Browse the repository at this point in the history

  19. Adding lyaer wise logging

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    360fef4 View commit details
    Browse the repository at this point in the history

  20. shard ids

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    c23d616 View commit details
    Browse the repository at this point in the history

  21. Loading qzero correctly

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    8d81d14 View commit details
    Browse the repository at this point in the history

  22. List operand

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    22e1aa7 View commit details
    Browse the repository at this point in the history

  23. If clause

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    81e01f3 View commit details
    Browse the repository at this point in the history

  24. Able to load layers

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    dcfd32d View commit details
    Browse the repository at this point in the history

  25. Setting load quant to false

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    f04cbea View commit details
    Browse the repository at this point in the history

  26. Disabling logging

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 12, 2024
    Configuration menu
    Copy the full SHA
    a56821d View commit details
    Browse the repository at this point in the history

Commits on Aug 13, 2024

  1. Removing *2 in marlin moe repack

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    7f961c6 View commit details
    Browse the repository at this point in the history

  2. *4 in marlin moe repack

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    4a6c7ff View commit details
    Browse the repository at this point in the history

  3. bits

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    e6cd286 View commit details
    Browse the repository at this point in the history

  4. *4

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    90241c4 View commit details
    Browse the repository at this point in the history

  5. intermediate size

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    67409e9 View commit details
    Browse the repository at this point in the history

  6. repeat keyword

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    539032e View commit details
    Browse the repository at this point in the history

  7. hidden size

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    57b1cbe View commit details
    Browse the repository at this point in the history

  8. intermediate size back

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    87f1dd4 View commit details
    Browse the repository at this point in the history

  9. permute scales w3

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    4c073c2 View commit details
    Browse the repository at this point in the history

  10. *2

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    d732493 View commit details
    Browse the repository at this point in the history

  11. log

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    fdc22c4 View commit details
    Browse the repository at this point in the history

  12. shape as 2

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    272822e View commit details
    Browse the repository at this point in the history

  13. test

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    3ce045e View commit details
    Browse the repository at this point in the history

  14. Increasing to 4 and changing assert

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    c4ba477 View commit details
    Browse the repository at this point in the history

  15. logging

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    2ea8370 View commit details
    Browse the repository at this point in the history

  16. marlin moe repack change

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    8287025 View commit details
    Browse the repository at this point in the history

  17. mult qweight shape by pack factor

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    53b23b9 View commit details
    Browse the repository at this point in the history

  18. Potential support for 8 bit

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    bc40786 View commit details
    Browse the repository at this point in the history

  19. undo change

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    bea13de View commit details
    Browse the repository at this point in the history

  20. qzeros

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    a3a9114 View commit details
    Browse the repository at this point in the history

  21. switching traffic to mixtral quant

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    eb916f9 View commit details
    Browse the repository at this point in the history

  22. compat

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    017d6f8 View commit details
    Browse the repository at this point in the history

  23. Passing intermediate tensor into mixtral in quant file

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    eb9c087 View commit details
    Browse the repository at this point in the history

  24. Removing intemediate tensors from forward

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    ea3cf18 View commit details
    Browse the repository at this point in the history

  25. load weights from quant

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    4f6b4ca View commit details
    Browse the repository at this point in the history

  26. Mixtral load weights change:

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    7ec27d9 View commit details
    Browse the repository at this point in the history

  27. none shard id change

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    aa1fe77 View commit details
    Browse the repository at this point in the history

Commits on Aug 15, 2024

  1. Use class from mixtral_quant

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    ae8fb15 View commit details
    Browse the repository at this point in the history

  2. Removing lora from mixtral model init

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    b863981 View commit details
    Browse the repository at this point in the history

  3. Adding empty intermediate tensors

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    5556d28 View commit details
    Browse the repository at this point in the history

  4. Building quantMixtralModel

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    c484a37 View commit details
    Browse the repository at this point in the history

  5. fused moe test

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    0344e72 View commit details
    Browse the repository at this point in the history

  6. Lora enabled mixtral

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    8c8b3fa View commit details
    Browse the repository at this point in the history

  7. LoRAMixtralModel compat

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    dff59cd View commit details
    Browse the repository at this point in the history

  8. remove prefix

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    33f7e51 View commit details
    Browse the repository at this point in the history

  9. use fused moe

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    fdba917 View commit details
    Browse the repository at this point in the history

  10. remove org num embeddings

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    780471e View commit details
    Browse the repository at this point in the history

  11. pass use fused moe into decoder

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    c0970f1 View commit details
    Browse the repository at this point in the history

  12. Mixtral for causal lm load func

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    6a1a838 View commit details
    Browse the repository at this point in the history

  13. Copying over quant mixtral

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    5c3e857 View commit details
    Browse the repository at this point in the history

  14. Passing prefix

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    8d327de View commit details
    Browse the repository at this point in the history

  15. Weight load

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    d337aea View commit details
    Browse the repository at this point in the history

  16. Weight load back

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    379f3e8 View commit details
    Browse the repository at this point in the history

  17. Load with name not weight name

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    a5d356e View commit details
    Browse the repository at this point in the history

  18. params dict should load from old name

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    62c0135 View commit details
    Browse the repository at this point in the history

  19. logging name and parmas

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    d23c00c View commit details
    Browse the repository at this point in the history

  20. log expert parmas map

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    6dda447 View commit details
    Browse the repository at this point in the history

  21. parity with prev commits

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    67ce7b6 View commit details
    Browse the repository at this point in the history

  22. Adding qzeros to mapping

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    bd933c9 View commit details
    Browse the repository at this point in the history

  23. Remove log

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    77cd095 View commit details
    Browse the repository at this point in the history

  24. Remove is quantized

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    529191e View commit details
    Browse the repository at this point in the history

  25. Assume fused true

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    2450543 View commit details
    Browse the repository at this point in the history

  26. rm fused true

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    8cba45e View commit details
    Browse the repository at this point in the history

  27. Switching to mixtral moe

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    10940a5 View commit details
    Browse the repository at this point in the history

  28. Precision changes

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    895ffbe View commit details
    Browse the repository at this point in the history

  29. Cleanup

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    e54b2e4 View commit details
    Browse the repository at this point in the history

  30. Mixtral quant parity:

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    b4f23dc View commit details
    Browse the repository at this point in the history

  31. fixing tests

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    d59fe3b View commit details
    Browse the repository at this point in the history

  32. Tests working and correctness verified

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    0d9cbdc View commit details
    Browse the repository at this point in the history

  33. Formating

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    112aa40 View commit details
    Browse the repository at this point in the history

Commits on Aug 19, 2024

  1. Moving single marlin alongside fused marlin

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 19, 2024
    Configuration menu
    Copy the full SHA
    1ca9098 View commit details
    Browse the repository at this point in the history

  2. Removing unused imports

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 19, 2024
    Configuration menu
    Copy the full SHA
    4d41425 View commit details
    Browse the repository at this point in the history

  3. single marlin moe import

    @DhruvaBansal00
    DhruvaBansal00 committed Aug 19, 2024
    Configuration menu
    Copy the full SHA
    4907f43 View commit details
    Browse the repository at this point in the history

Commits on Aug 20, 2024

  1. Merge branch 'main' into marlin-moe-integration

    @ElizaWszola
    ElizaWszola committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    8f4648c View commit details
    Browse the repository at this point in the history

  2. Merge branch 'marlin-moe-integration' into gptq-marlin-refactor

    @ElizaWszola
    ElizaWszola committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    8225037 View commit details
    Browse the repository at this point in the history

Commits on Aug 21, 2024

  1. Unify shard_id to be of str w[1-3] format

    @ElizaWszola
    ElizaWszola committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    315e3b6 View commit details
    Browse the repository at this point in the history

Commits on Aug 22, 2024

  1. Merge pull request #4 from DhruvaBansal00/gptq-marlin-refactor 

    Refactoring for maintainability
    @ElizaWszola
    ElizaWszola authored Aug 22, 2024
    Configuration menu
    Copy the full SHA
    34bb5b0 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into marlin-moe-integration

    @ElizaWszola
    ElizaWszola committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    fd4bb21 View commit details
    Browse the repository at this point in the history

Commits on Aug 26, 2024

  1. Unfused codepath for non-supported quant_types

    @ElizaWszola
    ElizaWszola committed Aug 26, 2024
    Configuration menu
    Copy the full SHA
    7956a69 View commit details
    Browse the repository at this point in the history

Commits on Aug 28, 2024

  1. uint8b128 support

    @ElizaWszola
    ElizaWszola committed Aug 28, 2024
    Configuration menu
    Copy the full SHA
    2511f78 View commit details
    Browse the repository at this point in the history

Commits on Aug 29, 2024

  1. Merge branch 'main' into marlin-moe-integration

    @ElizaWszola
    ElizaWszola committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    f875842 View commit details
    Browse the repository at this point in the history

  2. Cleanup, compressed tensors compatibility

    @ElizaWszola
    ElizaWszola committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    d8feb8d View commit details
    Browse the repository at this point in the history

  3. update todo

    @ElizaWszola
    ElizaWszola committed Aug 29, 2024
    Configuration menu
    Copy the full SHA
    3676621 View commit details
    Browse the repository at this point in the history

Commits on Aug 30, 2024

  1. Fix merge

    @ElizaWszola
    ElizaWszola committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    75e3dd5 View commit details
    Browse the repository at this point in the history

  2. bad paste

    @ElizaWszola
    ElizaWszola committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    a5f5a74 View commit details
    Browse the repository at this point in the history

Commits on Sep 2, 2024

  1. GPTQFusedMoE layer

    @ElizaWszola
    ElizaWszola committed Sep 2, 2024
    Configuration menu
    Copy the full SHA
    e305306 View commit details
    Browse the repository at this point in the history