|
Accuracy drop after model quantization
|
|
3
|
697
|
November 4, 2023
|
|
What's the supported datatype for activation in torch.ao.nn.quantized.linear?
|
|
2
|
468
|
November 4, 2023
|
|
Accuracy drop after prepare_qat_fx with no quantization
|
|
2
|
401
|
November 1, 2023
|
|
Why does an unsigned torch.quint8 tensor have a sign?
|
|
6
|
939
|
November 1, 2023
|
|
Quantization of ssdlite from torchvision
|
|
1
|
414
|
October 26, 2023
|
|
RuntimeError: Unsupported qscheme: per_channel_affine during fx qat
|
|
8
|
2210
|
October 17, 2023
|
|
Static quantization for Transformer block : AttributeError 'function' object has no attribute 'is_cuda'
|
|
5
|
808
|
October 13, 2023
|
|
Quantization official example
|
|
11
|
947
|
October 13, 2023
|
|
Quantization of a single tensor
|
|
3
|
996
|
October 12, 2023
|
|
Custom Quantization using PT2 -> q/dq representation
|
|
1
|
453
|
October 12, 2023
|
|
Quantization of a pytorch model
|
|
1
|
419
|
October 12, 2023
|
|
Mixed Precision Training and Quantisation Aware Training together
|
|
1
|
670
|
October 12, 2023
|
|
How to let the two input nodes of `add` op share the same quantization params(scale and zero point)?
|
|
2
|
502
|
October 9, 2023
|
|
Quantization of multi_head_attention_forward
|
|
11
|
2642
|
October 4, 2023
|
|
Error trying to quantize Transformer model
|
|
2
|
695
|
October 3, 2023
|
|
How to train non quantized layers of quantized model on GPU
|
|
1
|
425
|
October 3, 2023
|
|
Torchscript with dynamic quantization produces inconsistent model outputs in Python and Java
|
|
9
|
925
|
October 3, 2023
|
|
Is bias quantized while doing pytorch static quantization?
|
|
18
|
5258
|
September 27, 2023
|
|
Quantized model profiling
|
|
12
|
982
|
September 26, 2023
|
|
Pointers to bring quantized models to device
|
|
8
|
1774
|
September 26, 2023
|
|
Model size reduction
|
|
1
|
397
|
September 26, 2023
|
|
Understanding differences in the default qconfig for fbgemm and qnnpack
|
|
15
|
1501
|
September 22, 2023
|
|
What do [De]QuantStub actually do?
|
|
8
|
6863
|
September 21, 2023
|
|
The ONNX exported by my QAT quantization training does not have a fake operator, the code is as follows?
|
|
4
|
847
|
September 19, 2023
|
|
RFC-0019 Extending PyTorch Quantization to Custom Backends
|
|
2
|
448
|
September 19, 2023
|
|
Quantizion partially applied to a PyTorch model
|
|
1
|
629
|
September 15, 2023
|
|
LSTM Quantization
|
|
1
|
619
|
September 14, 2023
|
|
Can the output of operator QuantizedConv2d is fp32?
|
|
4
|
412
|
September 12, 2023
|
|
Questions about preparing QAT model
|
|
6
|
1160
|
September 12, 2023
|
|
Can we use int8 activation quantization in pytorch
|
|
3
|
1008
|
September 1, 2023
|