
1★
Edge Model Compression
@[anonymous]
Applies pruning, quantization, distillation, and architecture search to optimize models for edge deployment.
Skill rank progression over time. Hover for details.
All named implementations attributed to @majiayu000 in the registry.

Applies pruning, quantization, distillation, and architecture search to optimize models for edge deployment.
Want to add more skills?
Register your repo →