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

fast fp16 seq and one mode #157

Open
wants to merge 20 commits into
base: main
Choose a base branch
from
Open

fast fp16 seq and one mode #157

wants to merge 20 commits into from

Conversation

daquexian
Copy link
Contributor

@daquexian daquexian commented Jul 25, 2023

2080 1.5B model, cuda fp16:

main this PR
one mode 0.3496s 0.2191s
seq mode 0.0202s 0.0123s

GPU memory usage keeps the same with main branch.

Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Signed-off-by: daquexian <daquexian566@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant