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.

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

Refactor turbomind attention by precomputing cos/sin #2801

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Commits on Nov 25, 2024

  1. use precomputed cos sin

    irexyc committed Nov 25, 2024
    Configuration menu
    Copy the full SHA
    05d011c View commit details
    Browse the repository at this point in the history
  2. remove unused

    irexyc committed Nov 25, 2024
    Configuration menu
    Copy the full SHA
    7b74b72 View commit details
    Browse the repository at this point in the history
  3. Configuration menu
    Copy the full SHA
    589cacb View commit details
    Browse the repository at this point in the history

Commits on Dec 2, 2024

  1. Configuration menu
    Copy the full SHA
    45f0968 View commit details
    Browse the repository at this point in the history
  2. split rope params

    irexyc committed Dec 2, 2024
    Configuration menu
    Copy the full SHA
    0e4c315 View commit details
    Browse the repository at this point in the history
  3. remove prefix yarn_, llama3_

    irexyc committed Dec 2, 2024
    Configuration menu
    Copy the full SHA
    ea6112e View commit details
    Browse the repository at this point in the history
  4. fix test_attention

    irexyc committed Dec 2, 2024
    Configuration menu
    Copy the full SHA
    0513e12 View commit details
    Browse the repository at this point in the history