-
Notifications
You must be signed in to change notification settings - Fork 2
Shadi/release #20
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
base: dan/release
Are you sure you want to change the base?
Shadi/release #20
Conversation
* Fixed: Slicer metadata not properly locating sliced files * Fixed: Saving to external output directory * Fixed metadata.json segment file paths * Fixed Run, Circuitize File Imports Slice, Circuitize, Run, Prove, Verify all functional with external directories * Added E2E Test (#10) * Added GA, Modified Circuitizer File Paths * Added Testing{ * Fix 14 (#15) * Fixed #14 * Update test.yml * Update test.yml
Added additional test + fixed slicing adding more segment directories than neccesary
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR adds GitHub workflow templates and comprehensive infrastructure for ONNX model analysis, slicing, and zero-knowledge proof generation. The changes introduce a complete pipeline for processing neural network models with support for multiple proof systems (EZKL, JSTProve) and include E2E testing capabilities.
- Adds comprehensive ONNX model analysis and slicing infrastructure with metadata generation
- Implements runners for multiple ZK proof systems (EZKL, JSTProve, DeepProve) with support for both whole model and sliced inference
- Introduces extensive testing framework with E2E tests and model generation utilities
Reviewed Changes
Copilot reviewed 21 out of 28 changed files in this pull request and generated 8 comments.
Show a summary per file
| File | Description |
|---|---|
| testing/core/e2e_tests/test_e2e.py | E2E test framework for the complete kubz workflow from slicing to verification |
| src/utils/onnx_utils.py | ONNX utility functions for model manipulation and metadata handling |
| src/utils/onnx_analyzer.py | Comprehensive ONNX model analyzer for extracting detailed model metadata |
| src/utils/model_generator.py | Test model generation utilities for creating various neural network architectures |
| src/utils/model_analyzer.py | PyTorch model analyzer for extracting activation functions and layer information |
| src/templates/report_template.html | Interactive HTML template for neural network visualization reports |
| src/runners/runner_utils.py | Shared utilities for model runners including memory monitoring and input preprocessing |
| src/runners/onnx_runner.py | ONNX model inference runner supporting both whole and sliced model execution |
| src/runners/model_runner.py | PyTorch model runner with support for segmented inference |
| src/runners/jstprove_runner.py | JSTProve integration for ZK proof generation and verification |
| src/runners/ezkl_runner.py | EZKL integration with comprehensive proof workflow support |
| src/runners/deepprove_runner.py | DeepProve runner skeleton for future ZK proof system integration |
| src/onnx_slicer.py | ONNX model slicing implementation for creating model segments |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
GITHUB PR TEMPLATE + WORKFLOWS