model : do not repack if a GPU device is present #12498
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
slaren
approved these changes
Mar 21, 2025
Ivy233
pushed a commit
to Ivy233/llama.cpp
that referenced
this pull request
Mar 23, 2025
Contributor
|
why disable and not simply change order: |
Member
Author
|
I think keeping the non-offloaded layers without repack would allow to dynamically move the ops to the GPU which would end up generally more efficient than using the optimized repacked CPU implementations. |
Contributor
|
Yes, I understood that you prefer to have dynamically move the ops to the GPU. |
Member
Author
|
Hm, I guess you might be right. Do you want to give this a try, or should I go ahead and create a PR. |
Contributor
|
OK. I'll have a try! => #12632 🤞 |
Djip007
pushed a commit
to Djip007/llama.cpp
that referenced
this pull request
Mar 28, 2025
this allow to use GPU host when possible over CPU repack. this have the same effect to resolve this issues (ggml-org#12498) without completely disable CPU extra buffer.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
fix #12481
fix #12490
ref #12481 (comment)
Disable repacking (i.e. extra buffer types) if a GPU device is going to be available.