|
Using AMP with QAT
|
|
1
|
612
|
August 27, 2024
|
|
Is bias quantized when I run pt2e quantization?
|
|
12
|
331
|
August 21, 2024
|
|
The results of torch.profiler() and time.time() do not match
|
|
8
|
1320
|
August 20, 2024
|
|
Reproduce qconv kernel for x86
|
|
4
|
249
|
August 19, 2024
|
|
Torch.jit.script does not work on a quantized model
|
|
6
|
452
|
August 14, 2024
|
|
Confusion Regarding Quantization on GPUs with PyTorch
|
|
1
|
296
|
August 13, 2024
|
|
Is fuse_fx supposed to preceed convert_fx in the quant pipeline?
|
|
1
|
162
|
August 9, 2024
|
|
How to adjust the model to eliminate errors in convert_fx()?
|
|
10
|
303
|
July 18, 2024
|
|
Relationship between GPU Memory Usage and Batch Size
|
|
8
|
9933
|
July 17, 2024
|
|
Question about QAT quantization with torch.fx
|
|
7
|
631
|
July 16, 2024
|
|
Fusing a QAT model post-training
|
|
4
|
475
|
July 2, 2024
|
|
Relative error greater than unit roundoff for torch.float16
|
|
1
|
147
|
July 2, 2024
|
|
QuantStub with values in [-128,127]
|
|
6
|
832
|
July 2, 2024
|
|
TypeError: quantized_add() missing 2 required positional arguments: 'op_scale' and 'op_zero_point'
|
|
8
|
1250
|
July 2, 2024
|
|
Pytorch quantized model to ONNX - quantized_decomposed::quantize_per_tensor Error
|
|
3
|
599
|
July 2, 2024
|
|
After the neural network is quantized, how to use the GPU to infer the model?
|
|
1
|
274
|
June 28, 2024
|
|
Input data range after quantization
|
|
1
|
270
|
June 28, 2024
|
|
Quantizer Backend for Linear Op intermittent failures (ExecuTorch)
|
|
6
|
604
|
June 28, 2024
|
|
Random quantization
|
|
1
|
272
|
June 15, 2024
|
|
Why are `torch.bool`'s elements 1 byte and not 1 bit?
|
|
2
|
1158
|
June 8, 2024
|
|
Implementing Quantized Linear Layer in Numpy
|
|
2
|
815
|
June 8, 2024
|
|
Accessing input/output of unnamed functional layers via hooks
|
|
3
|
278
|
June 3, 2024
|
|
Inference error after int8 quantization with pytorch
|
|
12
|
3223
|
June 3, 2024
|
|
Qlinear (ONEDNN): data type of input should be QUint8
|
|
2
|
549
|
June 3, 2024
|
|
How to export a correct quantized model to onnx format
|
|
6
|
2977
|
June 3, 2024
|
|
What's the use of `torch.bool` tensors?
|
|
1
|
265
|
June 1, 2024
|
|
Post Training Static Quantization API still uses float weights instead of int?
|
|
6
|
1824
|
May 29, 2024
|
|
Starting out with QAT
|
|
13
|
3536
|
May 29, 2024
|
|
Is `torch.ao.quantization` being migrated to `torchao.quantization`?
|
|
2
|
738
|
May 29, 2024
|
|
Accuracy Drop During Calibration (before Conversion) in Post Training Quantization
|
|
1
|
211
|
May 23, 2024
|