Skip to content

Support Qwen3 and Gemma3#81

Merged
alessiodevoto merged 4 commits intomainfrom
feat-qwen3-gemma3
Jun 16, 2025
Merged

Support Qwen3 and Gemma3#81
alessiodevoto merged 4 commits intomainfrom
feat-qwen3-gemma3

Conversation

@alessiodevoto
Copy link
Copy Markdown
Collaborator

This addresses #76 to support the QK normalization used in Gemma3 and Qwen3 (+ updates library version).

@SimJeg SimJeg self-assigned this Jun 12, 2025
@alessiodevoto alessiodevoto force-pushed the feat-qwen3-gemma3 branch 2 times, most recently from 9ab6c0f to e9d2ad9 Compare June 12, 2025 12:24
Signed-off-by: alessiodevoto <devoto.alessio@gmail.com>
Signed-off-by: alessiodevoto <devoto.alessio@gmail.com>
@SimJeg
Copy link
Copy Markdown
Collaborator

SimJeg commented Jun 13, 2025

Also @alessiodevoto please check if issue #80 involves other changes in this PR

Signed-off-by: alessiodevoto <devoto.alessio@gmail.com>
@alessiodevoto
Copy link
Copy Markdown
Collaborator Author

@SimJeg fixed the comments, thanks! I left #80 for a different PR for now

Signed-off-by: alessiodevoto <devoto.alessio@gmail.com>
@alessiodevoto alessiodevoto merged commit f7d77d3 into main Jun 16, 2025
3 checks passed
@alessiodevoto alessiodevoto deleted the feat-qwen3-gemma3 branch June 16, 2025 09:40
@SimJeg SimJeg linked an issue Jun 16, 2025 that may be closed by this pull request
maxjeblick pushed a commit that referenced this pull request Aug 12, 2025
Signed-off-by: Max Jeblick <maximilianjeblick@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.

Add support for Qwen3 and Gemma3

2 participants