Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature Branch] Quant modifier UX #2263

Merged
merged 8 commits into from
May 22, 2024
Merged

[Feature Branch] Quant modifier UX #2263

merged 8 commits into from
May 22, 2024

Conversation

rahul-tuli
Copy link
Member

@rahul-tuli rahul-tuli commented May 2, 2024

Quantization Modifier UX Update

Description

This PR refactors the quantization modifiers to enhance user experience and simplify the system architecture. It is based off of changes from the sa/quant_mod_refactor main branch, all subsequent changes will be merged as smaller bites sized PRs into this. Key updates include:

Reference Documentation

For more detailed information about the changes and their impact, please refer to the documentation here.

@rahul-tuli rahul-tuli changed the base branch from main to sa/quant_mod_refactor May 2, 2024 15:31
Base automatically changed from sa/quant_mod_refactor to main May 6, 2024 20:02
@rahul-tuli rahul-tuli force-pushed the quant-modifier-ux branch 3 times, most recently from dfb3d7f to a55f50c Compare May 9, 2024 14:45
@rahul-tuli rahul-tuli marked this pull request as ready for review May 13, 2024 14:16
@rahul-tuli rahul-tuli changed the title [WIP][Feature Branch] Quant modifier UX [Feature Branch] Quant modifier UX May 13, 2024
@rahul-tuli rahul-tuli self-assigned this May 13, 2024
Make sparsegpt not inherit from wanda modifier
Decouple SparseGPTModifierPyTorch from WandaPruningModifier
Fix docstrings
rahul-tuli and others added 6 commits May 20, 2024 14:56
* Update OBCQ

* Extract GPTQ Modifier
…antization (#2294)

* Update OBCQ

* Extract GPTQ Modifier

* Update test recipes
* 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>
Copy link

@Satrat Satrat left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM once the tests pass

@bfineran bfineran merged commit c24e97f into main May 22, 2024
14 of 17 checks passed
@bfineran bfineran deleted the quant-modifier-ux branch May 22, 2024 18:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants