PyTorch Quantization
· Batch Import
Description
Model optimization techniques using INT8 quantization for size reduction and inference acceleration, supporting Post-Training Quantization (PTQ) and Quantization Aware Training (QAT) on FBGEMM and QNNPACK backends.
Repository
https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/pytorch-quantization
View on GitHub