| | marlin_qqq | |
| | prototype | |
| | qat | |
| | __init__.py | 5.7 KB |
| | autoquant.py | 47.3 KB |
| | dynamic_quant.py | 2.7 KB |
| | GPTQ_MT.py | 32.5 KB |
| | GPTQ.py | 46.0 KB |
| | granularity.py | 2.8 KB |
| | linear_activation_quantized_tensor.py | 8.7 KB |
| | linear_activation_scale.py | 5.0 KB |
| | linear_activation_weight_observed_tensor.py | 5.5 KB |
| | observer.py | 6.9 KB |
| | quant_api.py | 57.7 KB |
| | quant_primitives.py | 50.4 KB |
| | README.md | 32.3 KB |
| | smoothquant.py | 9.9 KB |
| | subclass.py | 20.5 KB |
| | transform_module.py | 1.5 KB |
| | unified.py | 1.1 KB |
| | utils.py | 17.6 KB |
| | weight_only.py | 3.9 KB |
| | weight_tensor_linear_activation_quantization.py | 7.1 KB |