microsoft / microsoft/winml-cli
P0-FEATURE-010: Graph Optimizer - More Advanced Optimizations
Open
Nobody has claimed this yet.
feature scale
graph-optimizer
P1
triaged
- Dominant language
- Python
- Stars
- 40
- Forks
- 11
- Avg merge
- 1d 8h
- Merged PRs (30d)
- 50
Description
Summary
Implement advanced graph optimizations including Cast movement and NonZero elimination.
Context
- Priority: P0.17
- Category: Feature Scale - Graph Optimizer
Scope
- Move Cast around non-compute ops (reduce precision conversion overhead)
- NonZero elimination (remove unnecessary NonZero ops)
- Advanced fusion patterns
- EP-friendly graph transformations
Acceptance Criteria
- Cast movement optimization implemented
- NonZero elimination working
- Advanced fusion patterns applied
- Validated on P0 models with no regressions
References
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading plans/release/0315_release_plan/feature-scale.md to identify the graph optimizer entry points, supported patterns, and P0 validation models. Define and validate Cast movement, NonZero elimination, and advanced fusion patterns, then run the referenced P0 model checks and confirm there are no regressions.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100