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

ggml: bugfix: fix the inactive elements is agnostic for risc-v vector #8748

Merged
merged 1 commit into from
Jul 29, 2024

Conversation

CarterLi999
Copy link
Contributor

In these codes, we want to retain the value that they previously held when mask[i] is false. So we should use undisturbed. With the default agnostic policy of rvv intrinsic, these values can be held or be written with 1s.

In these codes, we want to retain the value that they previously held
when mask[i] is false. So we should use undisturbed. With the default
agnostic policy of rvv intrinsic, these values can be held or be
written with 1s.
@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Jul 29, 2024
@slaren
Copy link
Collaborator

slaren commented Jul 29, 2024

@Tameem-10xE could you review this change?

@Tameem-10xE
Copy link
Contributor

Tameem-10xE commented Jul 29, 2024

Thanks @CarterLi999 for catching this! @slaren the changes look good to me.

@slaren slaren merged commit 75af08c into ggerganov:master Jul 29, 2024
53 checks passed
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Aug 2, 2024
…ggerganov#8748)

In these codes, we want to retain the value that they previously held
when mask[i] is false. So we should use undisturbed. With the default
agnostic policy of rvv intrinsic, these values can be held or be
written with 1s.

Co-authored-by: carter.li <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ggml changes relating to the ggml tensor library for machine learning
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants