Revert naive compression format #32
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
bfineran
approved these changes
Jul 22, 2024
Satrat
changed the title
robertgshaw2-redhat
approved these changes
Jul 22, 2024
markmc
pushed a commit
to markmc/llm-compressor
that referenced
this pull request
Nov 13, 2024
* group size * add logic in base observer * group size full lifecycle run * before vectorize the for loop * comments, todo add channelwise * chan wise impl * comments * fix channel wise * comments, validators * fix typo * tensor return error fix * fix sparseml-side of code and add per channel * pyndatic defaults * token wise quant * Update src/compressed_tensors/quantization/quant_args.py Co-authored-by: Benjamin Fineran <[email protected]> * comments' * update dim * shape consistency * Update src/compressed_tensors/quantization/lifecycle/forward.py Co-authored-by: Benjamin Fineran <[email protected]> * comments * pass test_quant_args --------- Co-authored-by: Benjamin Fineran <[email protected]>
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Outdated suggestions cannot be applied.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.
SUMMARY:
Rather than float and int quantization sharing a format, we infer int-quantized for uniform integer quantization and float-quantized for uniform fp8 quantization. Any non-uniform quantization will still default to naive-quantized
TEST PLAN:
Updated unit test with new expected defaults