Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: vectorch-ai/ScaleLLM
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v0.1.9
Choose a base ref
...
head repository: vectorch-ai/ScaleLLM
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v0.2.0
Choose a head ref
  • 15 commits
  • 89 files changed
  • 1 contributor

Commits on Aug 6, 2024

  1. kernel: port softcap support for flash attention (#298)

    @guocuimi
    guocuimi authored Aug 6, 2024
    Configuration menu
    Copy the full SHA
    1c09cfd View commit details
    Browse the repository at this point in the history

  2. test: added unittests for attention sliding window (#299)

    @guocuimi
    guocuimi authored Aug 6, 2024
    Configuration menu
    Copy the full SHA
    69a4cfc View commit details
    Browse the repository at this point in the history

  3. model: added gemma2 with softcap and sliding window support (#300)

    @guocuimi
    guocuimi authored Aug 6, 2024
    Configuration menu
    Copy the full SHA
    f8ad478 View commit details
    Browse the repository at this point in the history

Commits on Aug 7, 2024

  1. kernel: support kernel test in python via pybind (#301)

    @guocuimi
    guocuimi authored Aug 7, 2024
    Configuration menu
    Copy the full SHA
    c97758e View commit details
    Browse the repository at this point in the history

Commits on Aug 8, 2024

  1. test: added unittests for marlin fp16xint4 gemm (#302)

    @guocuimi
    guocuimi authored Aug 8, 2024
    Configuration menu
    Copy the full SHA
    8afce60 View commit details
    Browse the repository at this point in the history

  2. docs: added doc for marlin int4 format

    @guocuimi
    guocuimi committed Aug 8, 2024
    Configuration menu
    Copy the full SHA
    986a87a View commit details
    Browse the repository at this point in the history

Commits on Aug 9, 2024

  1. fix: move eos out of stop token list to honor ignore_eos option (#305)

    @guocuimi
    guocuimi authored Aug 9, 2024
    Configuration menu
    Copy the full SHA
    bc29937 View commit details
    Browse the repository at this point in the history

  2. refactor: move models to upper folder (#306)

    @guocuimi
    guocuimi authored Aug 9, 2024
    Configuration menu
    Copy the full SHA
    9dcc4ba View commit details
    Browse the repository at this point in the history

Commits on Aug 14, 2024

  1. kernel: port gptq marlin kernel and fp8 marlin kernel (#307)

    @guocuimi
    guocuimi authored Aug 14, 2024
    Configuration menu
    Copy the full SHA
    6c9e8a1 View commit details
    Browse the repository at this point in the history

  2. rust: upgrade rust libs to latest version (#309)

    @guocuimi
    guocuimi authored Aug 14, 2024
    Configuration menu
    Copy the full SHA
    5d1f0c4 View commit details
    Browse the repository at this point in the history

Commits on Aug 17, 2024

  1. refactor: remove the logic loading individual weight from shared part… 

    …itions (#311)
    @guocuimi
    guocuimi authored Aug 17, 2024
    Configuration menu
    Copy the full SHA
    a645fd2 View commit details
    Browse the repository at this point in the history

Commits on Aug 19, 2024

  1. feat: added fused column parallel linear (#313)

    @guocuimi
    guocuimi authored Aug 19, 2024
    Configuration menu
    Copy the full SHA
    a8b8799 View commit details
    Browse the repository at this point in the history

  2. feat: added gptq marlin qlinear layer (#312)

    @guocuimi
    guocuimi authored Aug 19, 2024
    Configuration menu
    Copy the full SHA
    be88b66 View commit details
    Browse the repository at this point in the history

Commits on Aug 20, 2024

  1. kernel: port awq repack kernel (#314)

    @guocuimi
    guocuimi authored Aug 20, 2024
    Configuration menu
    Copy the full SHA
    91cfbb8 View commit details
    Browse the repository at this point in the history

Commits on Aug 21, 2024

  1. bump up version to 0.2.0

    @guocuimi
    guocuimi committed Aug 21, 2024
    Configuration menu
    Copy the full SHA
    96b8127 View commit details
    Browse the repository at this point in the history
Loading