Skip to content

Add 1-block scoring to the compress algorithm#625

Merged
danielkorzekwa merged 58 commits intofeature/compressfrom
dkorzekwa/scoring
Dec 2, 2025
Merged

Add 1-block scoring to the compress algorithm#625
danielkorzekwa merged 58 commits intofeature/compressfrom
dkorzekwa/scoring

Conversation

@danielkorzekwa
Copy link
Copy Markdown
Contributor

@danielkorzekwa danielkorzekwa commented Dec 2, 2025

What does this PR do?

Add 1-block scoring to the compress algorithm.

@danielkorzekwa
Add decilm modelling code
694c317 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm modelling code.
991659f 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add transformers codebase
8489cee 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add transformers code
f0afefe 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm modelling code
b3ed5bc 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm modelling code
a700da5 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Correct licence headers
b59b679 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Correct licence headers
1abdf3e 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm code
66609b1 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm code
7da0a8a 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm code
6e09a81 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm code
2e3f5da 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add decilm code
418890e 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Make llama3 converter self-contained (no deps on internal Nvidia code)
01f4fc1 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add common module
c57eed4 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
module refactoring
3dc37b3 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
refactoring
10ffdfe 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add shared_checkpointing_utils
27a4456 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add json tools
b0e22b7 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add logger
52e7827 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
f5c1c87 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add post_init_sparse module
0aa6320 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add post_init_sparse
35d0dbc 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
merginy hydra.py and hydra_utils.py
e39a1ad 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add integrationt test for attention pruning
1bd0c67 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add score_pruning_activations
0ecd52b 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
278c6b7 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add dist_utils
7a0af16 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add validate_model
0f0cbbd 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add activation scoring hooks for pruning
cb5cf25 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add sewing_kit
ca7ab3f 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add sewing_kit
a7a4adc 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
fix imports
ad84c26 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
fix imports
3d7e8a2 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add pruning_ckpts
3d755b2 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add pruning_ckpts
845d453 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
4fd921b 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
refactor imports
3641847 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
8d6333b 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add build_replacement_library
dcb86e2 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
dfd3adc 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add replacement_library
daf94d3 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
refactor imports
ab6e9e3 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
refactor imports
01a6aee 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add subblock_stats
79cf2cf 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
add subblock_stats
46d2ea2 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
561e04a 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
22da6b0 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
import refactoring
d4dd0d7 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Add scoring module
0a3b7f2 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
Merge branch 'feature/compress' into dkorzekwa/scoring
8d58c00 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa
delete noty used file
1b06f60 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa danielkorzekwa requested a review from a team as a code owner December 2, 2025 10:11
@danielkorzekwa
Add doc strings
6236dd5 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
kevalmorabia97
kevalmorabia97 approved these changes Dec 2, 2025
View reviewed changes
Copy link
Copy Markdown
Collaborator

@kevalmorabia97 kevalmorabia97 left a comment

Choose a reason for hiding this comment

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

minor comments. Feel free to merge after addressing them

modelopt/torch/_compress/tools/validate_puzzle_with_multi_replacements.py Outdated
Comment on lines +65 to +66
PUZZLE_DIR=".../Llama-3_2-1B-Instruct/parallel_puzzle";
PUZZLE_DIR=".../Llama-4-Scout-17B-16E-Instruct/attention_pruning";
Copy link
Copy Markdown
Collaborator

@kevalmorabia97 kevalmorabia97 Dec 2, 2025

Choose a reason for hiding this comment

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

why 2 PUZZLE_DIR env variables here? Seems confusing

Copy link
Copy Markdown
Contributor Author

@danielkorzekwa danielkorzekwa Dec 2, 2025

Choose a reason for hiding this comment

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

removed the second one

@codecov
Copy link
Copy Markdown

codecov bot commented Dec 2, 2025 •
edited
Loading

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 74.37%. Comparing base (954103e) to head (5212c21).
⚠️ Report is 1 commits behind head on feature/compress.

Additional details and impacted files 
@@                Coverage Diff                @@
##           feature/compress     #625   +/-   ##
=================================================
  Coverage             74.37%   74.37%           
=================================================
  Files                   182      182           
  Lines                 18219    18219           
=================================================
  Hits                  13550    13550           
  Misses                 4669     4669

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

danielkorzekwa and others added 2 commits December 2, 2025 11:36
@danielkorzekwa @kevalmorabia97
Update modelopt/torch/_compress/tools/validate_puzzle_with_multi_repl…
8424891 
…acements.py

Co-authored-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
Signed-off-by: Daniel Korzekwa <daniel.korzekwa@gmail.com>
@danielkorzekwa
Simplify docs
5212c21 
Signed-off-by: Daniel Korzekwa <dkorzekwa@nvidia.com>
@danielkorzekwa danielkorzekwa merged commit dcc425f into feature/compress Dec 2, 2025
21 checks passed
@danielkorzekwa danielkorzekwa deleted the dkorzekwa/scoring branch December 2, 2025 12:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@kevalmorabia97 kevalmorabia97 kevalmorabia97 approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@danielkorzekwa @kevalmorabia97