|
Kernel Dies When Testing a Quantized ResNet101 Model in PyTorch
|
|
2
|
95
|
December 12, 2024
|
|
Auto-cast and pytorch 2 export quantization
|
|
8
|
570
|
December 9, 2024
|
|
RuntimeError: Quantized cudnn conv2d is currenty limited to groups = 1; received groups =16 , during QAT
|
|
3
|
1073
|
December 6, 2024
|
|
Support for quantization in int16
|
|
5
|
316
|
December 5, 2024
|
|
Quantize a single tensor obtained from a float32 model
|
|
2
|
91
|
November 29, 2024
|
|
Simple quantisation reproduction - how to convert state dict to int8
|
|
1
|
105
|
November 27, 2024
|
|
torch.ao.nn.quantizable.modules.activation.MultiheadAttention not loading the pre-trained model weights correctly
|
|
1
|
75
|
November 27, 2024
|
|
QConfig for Resnet50 with weights dtype quint8
|
|
5
|
262
|
November 27, 2024
|
|
Load custom trained parameters into quantized model
|
|
1
|
92
|
November 27, 2024
|
|
Per channel setting for QAT Quantization
|
|
1
|
89
|
November 27, 2024
|
|
Custom QAT using ao.nn.qat modules, is this a valid approach?
|
|
1
|
108
|
November 27, 2024
|
|
Absence of qint32 in torch.ao.quantization.utils.weight_is_quantized
|
|
1
|
184
|
November 27, 2024
|
|
QAT QuantizedConv2d converted to ONNX format
|
|
1
|
226
|
November 27, 2024
|
|
Changing Qconfig to set datatype to int8
|
|
1
|
314
|
November 20, 2024
|
|
Inserting Unnecessary Fake Quants during QAT?
|
|
2
|
332
|
November 12, 2024
|
|
Torch.bfloat16 < how does it work? in bf 16 model
|
|
1
|
366
|
November 4, 2024
|
|
pytorch quantized linear function gives shape invalid error
|
|
3
|
257
|
November 1, 2024
|
|
How to lower to target backend?
|
|
3
|
360
|
November 1, 2024
|
|
Questions about build customized quantizer
|
|
1
|
394
|
October 23, 2024
|
|
Documentation about the Post Training Quantization not clear
|
|
6
|
294
|
October 23, 2024
|
|
Quantized model and Tensorrt deployment problem
|
|
1
|
89
|
October 22, 2024
|
|
Significant Accuracy Drop After "Custom" Activation Quantization – Seeking Debugging Suggestions
|
|
1
|
95
|
October 19, 2024
|
|
Is this for only Linux? ImportError: cannot import name 'quantize_' from 'torchao.quantization'
|
|
2
|
1517
|
October 17, 2024
|
|
Usage of tensor attributes in FX quantization
|
|
1
|
193
|
October 17, 2024
|
|
Isn't Bias normally int Quantized in INT8 PTSQ model?
|
|
1
|
148
|
October 9, 2024
|
|
Inference accuracy mismatch between original, quantized, dequantized model
|
|
2
|
278
|
September 18, 2024
|
|
Fixed scale and zero point with FixedQParamsObserver
|
|
2
|
609
|
September 12, 2024
|
|
Error in running quantised model RuntimeError: Could not run 'quantized::conv2d.new' with arguments from the 'CPU' backend
|
|
6
|
4406
|
August 29, 2024
|
|
Using AMP with QAT
|
|
1
|
608
|
August 27, 2024
|
|
Is bias quantized when I run pt2e quantization?
|
|
12
|
284
|
August 21, 2024
|