Vijay Janapa Reddi
4e1b536fac
Module 17: Export QuantizationComplete for INT8 quantization
- Added QuantizationComplete class with quantize/dequantize methods
- Exported quantization functions to tinytorch/optimization/quantization.py
- Provides 4x memory reduction with minimal accuracy loss
- Removed pedagogical QuantizedLinear export to avoid conflicts
- Added proper imports to export block
2025-11-06 15:50:48 -05:00
..
2025-09-30 13:41:00 -04:00
2025-09-25 11:16:28 -04:00
2025-09-30 13:41:00 -04:00
2025-11-05 19:10:52 -05:00
2025-09-25 11:16:28 -04:00
2025-11-06 12:30:39 -05:00
2025-11-05 19:10:52 -05:00
2025-09-30 17:15:40 -04:00
2025-11-06 15:50:48 -05:00
2025-09-25 11:16:28 -04:00
2025-11-06 14:21:22 -05:00
2025-09-25 11:16:28 -04:00
2025-11-05 19:10:52 -05:00
2025-09-30 08:58:58 -04:00
2025-09-30 13:51:30 -04:00
2025-11-06 15:50:48 -05:00