Skip to content

dflash: refactor draft model conversion#25110

Merged
ruixiang63 merged 2 commits into
ggml-org:masterfrom
ruixiang63:dflash_convert
Jun 28, 2026
Merged

dflash: refactor draft model conversion#25110
ruixiang63 merged 2 commits into
ggml-org:masterfrom
ruixiang63:dflash_convert

Conversation

@ruixiang63

Copy link
Copy Markdown
Member

Overview

Address comments in #22105 for DFlash conversion.

Additional information

Requirements

  • I have read and agree with the contributing guidelines
  • AI usage disclosure: Yes, for code review and figure out how to change

@ruixiang63 ruixiang63 requested a review from CISC as a code owner June 28, 2026 17:33
@ruixiang63

Copy link
Copy Markdown
Member Author

cc @CISC @ggerganov
Tested the new converted GGUF model locally, works well.

Comment thread gguf-py/gguf/constants.py
Comment thread conversion/qwen.py
@ruixiang63

Copy link
Copy Markdown
Member Author

I guess we need another approval, right?

@CISC CISC added the merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. label Jun 28, 2026
@CISC

CISC commented Jun 28, 2026

Copy link
Copy Markdown
Member

I guess we need another approval, right?

Or wait for someone to notice the merge ready label. :)

@ggerganov

Copy link
Copy Markdown
Member

@ruixiang63 You should be able to merge. Use squash-merge.

@CISC

CISC commented Jun 28, 2026

Copy link
Copy Markdown
Member

@ruixiang63 All yours. :)

@CISC CISC removed the merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. label Jun 28, 2026
@ruixiang63 ruixiang63 merged commit fa72bc6 into ggml-org:master Jun 28, 2026
5 checks passed
@ruixiang63

Copy link
Copy Markdown
Member Author

yeah, my first commit! Thanks guys!

@nipeone

nipeone commented Jun 29, 2026

Copy link
Copy Markdown

holy shit! finally merged!

Ankk98 added a commit to Ankk98/llama.cpp that referenced this pull request Jun 30, 2026
turbo-tan pushed a commit to turbo-tan/llama.cpp-tq3 that referenced this pull request Jul 1, 2026
* dflash: refactor draft model conversion

* apply fix for eagle3 convert
TheTom pushed a commit to TheTom/llama-cpp-turboquant that referenced this pull request Jul 2, 2026
* dflash: refactor draft model conversion

* apply fix for eagle3 convert
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants