Split SparseGPT and GPTQ modifiers #2272
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
rahul-tuli
force-pushed
the
quant-modifier-ux
branch
from
dfb3d7f
to
a55f50c
Compare
rahul-tuli
force-pushed
the
create-gptq-modifier
branch
2 times, most recently
from
863b7a7
to
49cd9e5
Compare
rahul-tuli
requested review from
Satrat,
dsikka,
bfineran,
horheynm and
dbogunowicz
rahul-tuli
changed the title
This was referenced May 9, 2024
Merged
Satrat
requested changes
May 15, 2024
rahul-tuli
force-pushed
the
quant-modifier-ux
branch
2 times, most recently
from
4230fb7
to
d4d85ff
Compare
rahul-tuli
force-pushed
the
create-gptq-modifier
branch
from
53b96e5
to
4409730
Compare
bfineran
approved these changes
May 20, 2024
bfineran
approved these changes
May 20, 2024
Absolutely, Good catch! I will add another PR once everything is in the feature branch, to prevent this PR from blowing up |
bfineran
pushed a commit
that referenced
this pull request
May 22, 2024
* Split WandaPruningModifier and SparseGPTModifier Make sparsegpt not inherit from wanda modifier Decouple SparseGPTModifierPyTorch from WandaPruningModifier Fix docstrings * Split SparseGPT and GPTQ modifiers (#2272) * Update OBCQ * Extract GPTQ Modifier * [GPTQ Modifier UX] Update tests to use GPTQModifier for obcq style quantization (#2294) * Update OBCQ * Extract GPTQ Modifier * Update test recipes * GPTQ UX config groups support (#2273) * Update OBCQ * Extract GPTQ Modifier * Update test recipes * Add config_groups support to GPTQModifier * mask_structure preservation test (#2284) * test * Preserve weight sparsity if greater than threshold * Add argument to preserve sparsity mask in SPARSEGPT * fix case when mask is none * Add test to check mask_structure - initial mask structure should be preserved b/w consecutive runs; added test to check this * Update tensor_follows_mask_structure to check for atleast n zeros --------- Co-authored-by: Sara Adkins <sara@neuralmagic.com> * PR comments --------- Co-authored-by: Sara Adkins <sara@neuralmagic.com> * Fix default case * Update test to use new vLLMQuantizationModifier * Style --------- Co-authored-by: Sara Adkins <sara@neuralmagic.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.
This PR introduces a structural change by separating concerns between quantization and sparsification. A new
GPTQModifieris extracted from the existingSparseGPTModifier. This ensures that each class now has a focused responsibility —GPTQModifiermanages quantization, whileSparseGPTModifieris dedicated to sparsification.Changes
Extraction of
GPTQModifier: Carved out fromSparseGPTModifier, this new class handles all aspects related to quantization, including arguments specifically for quantization processes.Refinement of
SparseGPTModifierandSparseGPTWrapper: These have been updated to solely focus on sparsification. All quantization-related functionalities have been removed.Creation of
GPTQWrapper: Implemented to apply quantization using OBQUpdate on Test Recipes: Modified the OBCQ test recipes to align with the new Modifiers.
Addition of Tests: Introduced new tests specifically for
GPTQModifierto ensure functionality and stability.Test Plan