Improve gguf tensor processing #34515
Open
Conversation
This file contains 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
|
Hey @SunMarc! I made some refactoring changes regarding tensor GGUF processing. Please, take a look. What do you think? |
VladOS95-cyber
force-pushed
the
improve-gguf-loading-system
branch
3 times, most recently
from
4b412ab
to
a090a84
Compare
|
Hey @SunMarc! Just a kind ping, does it make sense to have these changes? |
Isotr0py
reviewed
Nov 5, 2024
VladOS95-cyber
force-pushed
the
improve-gguf-loading-system
branch
from
a090a84
to
ddcea0f
Compare
VladOS95-cyber
force-pushed
the
improve-gguf-loading-system
branch
from
8876cc6
to
98810a3
Compare
Isotr0py
approved these changes
Nov 8, 2024
VladOS95-cyber
force-pushed
the
improve-gguf-loading-system
branch
from
98810a3
to
0060aac
Compare
VladOS95-cyber
force-pushed
the
improve-gguf-loading-system
branch
from
0060aac
to
254b073
Compare
|
Hey @SunMarc! Do you have any further comments or it looks good to you? |
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Outdated suggestions cannot be applied.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.
What does this PR do?
Adding more and more architectures with custom weights conversion is making tensor processing system bigger, less flexible and readable.
Improve GGUF tensor processing system in modeling_gguf_pytorch_utils.py by adding TensorProcessor class for general cases without custom weights changes and all necessary separated tensor processor classes based on architecture with custom process logic.
Before submitting
Pull Request section?
to it if that's the case. Link: Community contribution: Adding GGUF support for more architectures #33260
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Regarding the task @SunMarc @LysandreJik @ArthurZucker .