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

[onert] Support Q4_0 & Q8_0 FC weight #14182

Merged
merged 1 commit into from
Oct 10, 2024
Merged

Conversation

hseok-oh
Copy link
Contributor

@hseok-oh hseok-oh commented Oct 8, 2024

This commit enables supporting Q4_0 & Q8_0 FullyConnected OP weight.

ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh [email protected]


Related issue: #13909

This commit enables supporting Q4_0 & Q8_0 FullyConnected OP weight.

ONE-DCO-1.0-Signed-off-by: Hyeongseok Oh <[email protected]>
@hseok-oh hseok-oh added the PR/ready for review It is ready to review. Please review it. label Oct 8, 2024
@hseok-oh hseok-oh requested review from a team and glistening October 8, 2024 06:56

// get cplan
auto cplan = ggml_graph_plan(&graph, _external_context->ruy_context()->max_num_threads());
cplan.work_data = (uint8_t *)(malloc(cplan.work_size));
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(Optional)
How about using reinterpret_cast?

Suggested change
cplan.work_data = (uint8_t *)(malloc(cplan.work_size));
cplan.work_data = reinterpret_cast<uint8_t *>(malloc(cplan.work_size));

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'll update buffer usage later with gather OP.

Copy link
Contributor

@ragmani ragmani left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Contributor

@glistening glistening left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@hseok-oh
Copy link
Contributor Author

@nnfw-bot test all

@hseok-oh hseok-oh merged commit 2258da9 into Samsung:master Oct 10, 2024
9 checks passed
@hseok-oh hseok-oh deleted the draft/fc_ggml branch October 10, 2024 06:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
PR/ready for review It is ready to review. Please review it.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants