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

[DLIGHT][GPU] Improve matmul schedule for adreno #17430

Merged
merged 1 commit into from
Sep 30, 2024
Merged

[DLIGHT][GPU] Improve matmul schedule for adreno #17430

merged 1 commit into from
Sep 30, 2024

Commits on Sep 30, 2024

  1. [DLIGHT][GPU] Improve matmul schedule for adreno 

    Improved matmul schedule with layout transpose approach, which improves
as follows -
----Model-------prefill baseline ---------prefill optimized
--Llama-2-7b-------51 tok/sec --------------86 tok/sec
--Llama-3-8b-------48 tok/sec --------------79 tok/sec
--gemma-2b -------140 tok/sec -------------245 tok/sec

---------

Co-authored-by: krishnaraj36 <quic_kvegiraj@quicinc.com>
    @krishnaraj36
    krishnaraj36 committed Sep 30, 2024
    Configuration menu
    Copy the full SHA
    77221ca View commit details
    Browse the repository at this point in the history