Lightning-AI / Lightning-AI/lightning-thunder
Feature: Extend automated report tooling to identify subgraphs of FX graphs that are slow or have high memory usage
Open
Nobody has claimed this yet.
reporting
- Dominant language
- Python
- Stars
- 1.5k
- Forks
- 121
- PR merge metrics
- No merged PRs in 30d
Description
Once automated reports are running as expected and producing an analysis of each FX graph, we should try to extend the analysis to relevants parts of each FX graph. How we do this is TBD.
fyi @kiya00
Contributor guide
No contributing guide indexed for this repository
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 reviewing the existing automated report tooling and how it analyzes each FX graph. Clarify how relevant subgraphs should be selected and what thresholds define slow or high memory usage. Done means reports identify those problematic subgraphs consistently, but the issue does not name specific files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- performance, tooling
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100