Skip to content

Conversation

@hipudding
Copy link
Collaborator

@hipudding hipudding commented Jul 31, 2025

Improve loading efficiency after converting weights to NZ format.

@hipudding hipudding requested a review from ggerganov July 31, 2025 07:21
@github-actions github-actions bot added documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning Ascend NPU issues specific to Ascend NPUs labels Jul 31, 2025
Copy link
Collaborator

@noemotiovon noemotiovon left a comment

Choose a reason for hiding this comment

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

LGTM! Just one typo.

Copy link
Member

@ggerganov ggerganov left a comment

Choose a reason for hiding this comment

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

For my understanding - what is ND and NZ format?

@hipudding
Copy link
Collaborator Author

For my understanding - what is ND and NZ format?

Here's a describe about ND and NZ format . (You may need to translate this page.)
NZ will perform better on some Ascend hardware.

@hipudding hipudding merged commit 11490b3 into ggml-org:master Jul 31, 2025
51 of 52 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Ascend NPU issues specific to Ascend NPUs documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants