Quantization Compressor Support #45
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
added 11 commits
April 29, 2024 14:19
dbogunowicz
approved these changes
May 2, 2024
| from compressed_tensors.base import SPARSITY_CONFIG_NAME | ||
| from compressed_tensors.config import CompressionConfig | ||
| from compressed_tensors.config import SparsityCompressionConfig | ||
| from compressed_tensors.quantization import QuantizationConfig |
There was a problem hiding this comment.
nit: shouldn't all configs live side-by-side? the principle of least surprise?
Satrat
pushed a commit
that referenced
this pull request
May 7, 2024
* Compressed lifecycle implementation (INT8 only) * Apply suggestions from code review * small fixes for runtime * Quantization Compressor Support (#45) * add classes * WIP * moving around classes * code complete * tests passing * unit test bugs * fill out int decompression * docstrings * allow repeat frozens * int compressor unit tests * PR comments * fix device issue * fixing leaf checker * initial commit * Revert "Merge branch 'main' into compressed-lifecycle" This reverts commit 8dcdde5, reversing changes made to bb36936. * update version * fix test --------- Co-authored-by: Sara Adkins <sara@neuralmagic.com> Co-authored-by: dbogunowicz <damian@neuralmagic.com>
Satrat
pushed a commit
that referenced
this pull request
May 15, 2024
* group size * add logic in base observer * Compressed lifecycle implementation (INT8 only) * group size full lifecycle run * Apply suggestions from code review * before vectorize the for loop * comments, todo add channelwise * chan wise impl * comments * fix channel wise * comments, validators * fix typo * small fixes for runtime * add classes * tensor return error fix * WIP * moving around classes * 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 <bfineran@users.noreply.github.com> * comments' * code complete * tests passing * unit test bugs * fill out int decompression * docstrings * allow repeat frozens * update dim * int compressor unit tests * move helper * shape consistency * initial commit * first unit test passing * Update src/compressed_tensors/quantization/lifecycle/forward.py Co-authored-by: Benjamin Fineran <bfineran@users.noreply.github.com> * comments * tests passing * one more test * cleanup * pass test_quant_args * Quantization Compressor Support (#45) * add classes * WIP * moving around classes * code complete * tests passing * unit test bugs * fill out int decompression * docstrings * allow repeat frozens * int compressor unit tests * PR comments * fix device issue * fixing leaf checker * updating tests * docstrings * updating examples * update examples * fix channelwise * new tests, some fail * WIP * new helper fn * actually just a warning * group size speedups + fixes * group compression * fix output type on decompress * fix channelwise * revert * more tests * move tests * example notebook * add example notebook * update README * cleanup --------- Co-authored-by: George Ohashi <george@neuralmagic.com> Co-authored-by: Benjamin <ben@neuralmagic.com> Co-authored-by: Benjamin Fineran <bfineran@users.noreply.github.com>
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.
CompressionConfigtoSparsityCompressionConfig,QuantizationConfigis quantized versionModelCompressor->Compressor. This class still represents a single compression algorithm, either for sparsity or quantization. The "dense" compressor also applies to a model that has been quantized but not compressedModelCompressoris now a new class that handles the overall compression and decompression of both sparsity and quantization. Its responsible for model loading/saving as well as config loading/savingIntCompressorto represent a quantized model that has been compressed to its quantized type (ie float32 -> int8)Works with this SparseML PR: neuralmagic/sparseml#2260