feat: Extra debugging support for model conversion #15877
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…rt for llama-callback-eval and support for dumping intermediate steps in run-org-model.py
CISC
approved these changes
Sep 8, 2025
danbev
approved these changes
Sep 8, 2025
njsyw1997
pushed a commit
to aizip/llama.cpp
that referenced
this pull request
Sep 10, 2025
…gml-org#15877) * feat: Extra debugging support for model conversion - added BF16 support for llama-callback-eval and support for dumping intermediate steps in run-org-model.py
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
These are some things I've added while working on the Apertus conversion, thought they'd come in handy.
First of all, in the
examples/model_conversionscripts, I've addedllama-callback-eval-style dumping for intermediate steps when running the original model.Also added BF16 support for llama-callback-eval.