A comprehensive visualization and analysis tool for Triton IR files — helping developers analyze, debug, and understand Triton kernel compilation processes.
- 🚀 Launch Difference Analysis - Automatically detect and visualize variations in kernel launch parameters, helping you pinpoint performance bottlenecks and debug launch configurations.
- 🔍 Interactive Visualization - Explore Triton kernels with detailed metadata and stack traces
- 📊 Multi-format IR Support - View TTGIR, TTIR, LLIR, PTX, and AMDGCN in one place
- 🔄 Side-by-side Comparison - Compare IR stages with synchronized highlighting
- 📝 Structured Logging - Capture detailed compilation and launch events with source mapping
- 🌐 Ready-to-use Interface - No installation required, works in your browser
- 🔒 Privacy-first - All processing happens locally in your browser, no data uploaded
import tritonparse.structured_logging
# Initialize logging with launch tracing enabled
tritonparse.structured_logging.init("./logs/", enable_trace_launch=True)
# Your Triton/PyTorch code here
# ... your kernels ...
# Parse and generate trace files
import tritonparse.utils
tritonparse.utils.unified_parse("./logs/")The example terminal output is:
tritonparse log file list: /tmp/tmp1gan7zky/log_file_list.json
INFO:tritonparse:Copying parsed logs from /tmp/tmp1gan7zky to /scratch/findhao/tritonparse/tests/parsed_output
================================================================================
📁 TRITONPARSE PARSING RESULTS
================================================================================
📂 Parsed files directory: /scratch/findhao/tritonparse/tests/parsed_output
📊 Total files generated: 2
📄 Generated files:
--------------------------------------------------
1. 📝 dedicated_log_triton_trace_findhao__mapped.ndjson.gz (7.2KB)
2. 📝 log_file_list.json (181B)
================================================================================
✅ Parsing completed successfully!
================================================================================Visit https://pytorch-labs.github.io/tritonparse/ and open your local trace files (.ndjson.gz format).
🔒 Privacy Note: Your trace files are processed entirely in your browser - nothing is uploaded to any server!
For basic usage (trace generation):
git clone https://github.com/pytorch-labs/tritonparse.git
cd tritonparse
pip install -e .Prerequisites: Python ≥ 3.10, Triton > 3.3.1 (install from source), GPU required (NVIDIA/AMD)
TritonParse relies on new features in Triton > 3.3.1. Please install Triton from source for now.
| 📖 Guide | Description |
|---|---|
| 🏠 Wiki Home | Complete documentation and navigation |
| 📦 Installation Guide | Detailed setup for all scenarios |
| 📋 Usage Guide | Complete workflow and examples |
| 🌐 Web Interface Guide | Master the visualization interface |
| 🔧 Developer Guide | Contributing and development setup |
| ❓ FAQ | Frequently asked questions |
- Frontend: React 19, TypeScript, Vite, Tailwind CSS, Monaco Editor
- Backend: Python with Triton integration, structured logging
- Deployment: GitHub Pages, automatic deployment
TritonParse visualizes the complete Triton compilation pipeline:
Python Source → TTIR → TTGIR → LLIR → PTX/AMDGCN
Each stage can be inspected and compared to understand optimization transformations.
We welcome contributions! Please see our Developer Guide for:
- Development setup
- Code formatting standards
- Pull request process
- Architecture overview
- 🐛 Report Issues: GitHub Issues
- 💬 Discussions: GitHub Discussions
- 📚 Documentation: TritonParse Wiki
This project is licensed under the BSD-3 License - see the LICENSE file for details.
✨ Ready to get started? Visit our Installation Guide or try the online tool directly!