Custom QAT using ao.nn.qat modules, is this a valid approach?
|
|
1
|
29
|
November 27, 2024
|
Absence of qint32 in torch.ao.quantization.utils.weight_is_quantized
|
|
1
|
91
|
November 27, 2024
|
Questions on QAT for Wav2Vec
|
|
1
|
110
|
November 27, 2024
|
QAT QuantizedConv2d converted to ONNX format
|
|
1
|
89
|
November 27, 2024
|
Changing Qconfig to set datatype to int8
|
|
1
|
159
|
November 20, 2024
|
Inserting Unnecessary Fake Quants during QAT?
|
|
2
|
119
|
November 12, 2024
|
Torch.bfloat16 < how does it work? in bf 16 model
|
|
1
|
146
|
November 4, 2024
|
pytorch quantized linear function gives shape invalid error
|
|
3
|
118
|
November 1, 2024
|
How to lower to target backend?
|
|
3
|
157
|
November 1, 2024
|
Questions about build customized quantizer
|
|
1
|
341
|
October 23, 2024
|
Documentation about the Post Training Quantization not clear
|
|
6
|
89
|
October 23, 2024
|
Quantized model and Tensorrt deployment problem
|
|
1
|
27
|
October 22, 2024
|
Significant Accuracy Drop After "Custom" Activation Quantization – Seeking Debugging Suggestions
|
|
1
|
44
|
October 19, 2024
|
Is this for only Linux? ImportError: cannot import name 'quantize_' from 'torchao.quantization'
|
|
2
|
806
|
October 17, 2024
|
Usage of tensor attributes in FX quantization
|
|
1
|
92
|
October 17, 2024
|
Isn't Bias normally int Quantized in INT8 PTSQ model?
|
|
1
|
43
|
October 9, 2024
|
Inference accuracy mismatch between original, quantized, dequantized model
|
|
2
|
112
|
September 18, 2024
|
Fixed scale and zero point with FixedQParamsObserver
|
|
2
|
398
|
September 12, 2024
|
Error in running quantised model RuntimeError: Could not run 'quantized::conv2d.new' with arguments from the 'CPU' backend
|
|
6
|
3780
|
August 29, 2024
|
Using AMP with QAT
|
|
1
|
532
|
August 27, 2024
|
Is bias quantized when I run pt2e quantization?
|
|
12
|
112
|
August 21, 2024
|
The results of torch.profiler() and time.time() do not match
|
|
8
|
1146
|
August 20, 2024
|
Reproduce qconv kernel for x86
|
|
4
|
91
|
August 19, 2024
|
Torch.jit.script does not work on a quantized model
|
|
6
|
198
|
August 14, 2024
|
Confusion Regarding Quantization on GPUs with PyTorch
|
|
1
|
91
|
August 13, 2024
|
Is fuse_fx supposed to preceed convert_fx in the quant pipeline?
|
|
1
|
80
|
August 9, 2024
|
How to adjust the model to eliminate errors in convert_fx()?
|
|
10
|
200
|
July 18, 2024
|
Relationship between GPU Memory Usage and Batch Size
|
|
8
|
8204
|
July 17, 2024
|
Question about QAT quantization with torch.fx
|
|
7
|
310
|
July 16, 2024
|
Fusing a QAT model post-training
|
|
4
|
236
|
July 2, 2024
|