🚨 Support dequantization for most GGML types #32625
Merged
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
|
cc @SunMarc |
SunMarc
reviewed
Aug 12, 2024
5 tasks
5 tasks
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
SunMarc
reviewed
Aug 23, 2024
|
Nice ! Make sure to fix the CI with |
amyeroberts
approved these changes
Aug 27, 2024
There was a problem hiding this comment.
Nice! Thanks for enabling this
The min version requirement is technically a breaking change as older versions previously worked, however I think this is OK. Could you prefix the PR title with 🚨 to highlight this?
Overall, very nice, just a small thing to update and we're good to go!
Isotr0py
changed the title
zucchini-nlp
pushed a commit
to zucchini-nlp/transformers
that referenced
this pull request
Sep 3, 2024
* use gguf internal dequantize * add Q5_0 test * add iq1 test * add remained test * remove duplicated test * update docs * add gguf version limit * make style * update gguf import catch * revert vocab_size patch * make style * use GGUF_MIN_VERSION everywhere
|
Great job on this PR @Isotr0py 🙌 |
itazap
pushed a commit
to NielsRogge/transformers
that referenced
this pull request
Sep 20, 2024
* use gguf internal dequantize * add Q5_0 test * add iq1 test * add remained test * remove duplicated test * update docs * add gguf version limit * make style * update gguf import catch * revert vocab_size patch * make style * use GGUF_MIN_VERSION everywhere
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Outdated suggestions cannot be applied.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?
This PR needs to wait
ggufpackage version update and still work in progress.ggml_types. And clean up the current ggml dequantization implementation.llama.cpphas added numpy dequantization implementation ongguf-pyin gguf-py : Numpy dequantization for most types ggerganov/llama.cpp#8939, we can dequantize most of ggml tensor easily in one line.Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.