Skip to content

Latest commit

 

History

History
28 lines (21 loc) · 1.05 KB

File metadata and controls

28 lines (21 loc) · 1.05 KB

Contributing

We invite the community to replicate and challenge these results.

How to Contribute

  1. Replicate the surgery — Use the scripts in code/surgery/ on the same or different MoE models
  2. Measure on your hardware — Deploy to your own platform and measure power
  3. Calculate EPI — Use epi-bench
  4. Submit results — PR to data/community/ with your hardware description and measurements
  5. Discuss findings — Open a Discussion with observations, disagreements, or alternative analyses

Data Submission Format

data/community/<github-username>_<hardware>/
├── README.md              # Your setup description
├── run_<surgery_id>.json   # EPI result per configuration
├── power_trace_<id>.csv    # Power traces
└── benchmark_<id>.json     # Benchmark scores

Code Contributions

  • Surgery scripts for alternative MoE models
  • Alternative pruning strategies (not just router frequency)
  • Visualization improvements
  • Statistical analysis extensions