|
Model parameters and MACs
|
|
3
|
476
|
November 24, 2023
|
|
"How to quantize the bias of a convolution in QAT (Quantization Aware Training) mode?
|
|
1
|
615
|
November 22, 2023
|
|
Does PyTorch 2.1 Support Learnable Post-Training Quantization?
|
|
1
|
318
|
November 22, 2023
|
|
ONNX export of simple quantized model fails
|
|
10
|
2674
|
November 15, 2023
|
|
How to convert a model to ONNX before conversion?
|
|
0
|
430
|
November 14, 2023
|
|
The result of quantized conv2d is different from the result I calculate
|
|
4
|
1891
|
November 12, 2023
|
|
Unable to convert a quantized model to TorchScript
|
|
2
|
721
|
November 10, 2023
|
|
List of operations supported by QuantizedCPU backend
|
|
2
|
834
|
November 10, 2023
|
|
Is it possible to do int16 qat?
|
|
1
|
1212
|
November 10, 2023
|
|
Is the Static Quantization(PTSQ) model performs Integer-Arithmetic-Only Inference?
|
|
1
|
544
|
November 10, 2023
|
|
How does quantized conv2d handle scale and zero_point?
|
|
5
|
2233
|
November 9, 2023
|
|
Accuracy drop after model quantization
|
|
3
|
765
|
November 4, 2023
|
|
What's the supported datatype for activation in torch.ao.nn.quantized.linear?
|
|
2
|
499
|
November 4, 2023
|
|
Accuracy drop after prepare_qat_fx with no quantization
|
|
2
|
435
|
November 1, 2023
|
|
Why does an unsigned torch.quint8 tensor have a sign?
|
|
6
|
1025
|
November 1, 2023
|
|
Quantization of ssdlite from torchvision
|
|
1
|
441
|
October 26, 2023
|
|
RuntimeError: Unsupported qscheme: per_channel_affine during fx qat
|
|
8
|
2325
|
October 17, 2023
|
|
Static quantization for Transformer block : AttributeError 'function' object has no attribute 'is_cuda'
|
|
5
|
859
|
October 13, 2023
|
|
Quantization official example
|
|
11
|
1060
|
October 13, 2023
|
|
Quantization of a single tensor
|
|
3
|
1126
|
October 12, 2023
|
|
Custom Quantization using PT2 -> q/dq representation
|
|
1
|
478
|
October 12, 2023
|
|
Quantization of a pytorch model
|
|
1
|
435
|
October 12, 2023
|
|
Mixed Precision Training and Quantisation Aware Training together
|
|
1
|
728
|
October 12, 2023
|
|
How to let the two input nodes of `add` op share the same quantization params(scale and zero point)?
|
|
2
|
531
|
October 9, 2023
|
|
Quantization of multi_head_attention_forward
|
|
11
|
2845
|
October 4, 2023
|
|
Error trying to quantize Transformer model
|
|
2
|
731
|
October 3, 2023
|
|
How to train non quantized layers of quantized model on GPU
|
|
1
|
450
|
October 3, 2023
|
|
Torchscript with dynamic quantization produces inconsistent model outputs in Python and Java
|
|
9
|
1036
|
October 3, 2023
|
|
Is bias quantized while doing pytorch static quantization?
|
|
18
|
5476
|
September 27, 2023
|
|
Quantized model profiling
|
|
12
|
1075
|
September 26, 2023
|