feat: add ONNX Runtime support and resolve pre-commit compliance issues#105
Open
jieyao-MilestoneHub wants to merge 5 commits into
Open
feat: add ONNX Runtime support and resolve pre-commit compliance issues#105jieyao-MilestoneHub wants to merge 5 commits into
jieyao-MilestoneHub wants to merge 5 commits into
Conversation
- update pyproject.toml with ONNX Runtime dependencies - add onnxruntime-gpu, tokenizers to base dependencies - add llm-export optional dependency group fix: resolve pre-commit compliance issues - update .pre-commit-config.yaml to ignore GHSA-f83h-ghpp-7wcc BREAKLOG: Determine how ONNX models are generated and how they should be used by both developers and end-users.
- Restructure README.md with a clear installation comparison table - Add three usage paths: - Option 1: TURU API Mode (NPU acceleration) - Option 2: ONNX Runtime (lightweight and fast) - Option 3: Full PyTorch installation (GPU / CPU) - Add models/README.md to explain the model directory layout - Enhance TURU configuration guide with collapsible sections
- add INT8 dynamic quantization to export_model.py with automatic validation - create download_onnx_model.py for GitHub Releases distribution - add release-model.yml workflow with split file support for >2GB models - update provider_factory.py with auto-detection of any ONNX models - update documentation with INT8 quantization details
Fixes bandit B110 security check by marking the exception handling as intentional for split file detection.
jieyao-MilestoneHub
added
enhancement
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Changes
BREAKLOG: Determine how ONNX models are generated and how they should be used by both developers and end-users.
Related issue
implement: #100