About the quantization category
|
|
0
|
2386
|
October 2, 2019
|
Quantize a single tensor obtained from a float32 model
|
|
0
|
3
|
September 18, 2024
|
Inference accuracy mismatch between original, quantized, dequantized model
|
|
2
|
19
|
September 18, 2024
|
Fixed scale and zero point with FixedQParamsObserver
|
|
2
|
229
|
September 12, 2024
|
Significant Accuracy Drop After "Custom" Activation Quantization – Seeking Debugging Suggestions
|
|
0
|
31
|
September 11, 2024
|
Load custom trained parameters into quantized model
|
|
0
|
10
|
August 19, 2024
|
Error in running quantised model RuntimeError: Could not run 'quantized::conv2d.new' with arguments from the 'CPU' backend
|
|
6
|
3265
|
August 29, 2024
|
Using AMP with QAT
|
|
1
|
482
|
August 27, 2024
|
Is bias quantized when I run pt2e quantization?
|
|
12
|
59
|
August 21, 2024
|
The results of torch.profiler() and time.time() do not match
|
|
8
|
1087
|
August 20, 2024
|
Reproduce qconv kernel for x86
|
|
4
|
18
|
August 19, 2024
|
QConfig for Resnet50 with weights dtype quint8
|
|
4
|
32
|
August 19, 2024
|
Torch.jit.script does not work on a quantized model
|
|
6
|
55
|
August 14, 2024
|
Confusion Regarding Quantization on GPUs with PyTorch
|
|
1
|
17
|
August 13, 2024
|
torch.ao.nn.quantizable.modules.activation.MultiheadAttention not loading the pre-trained model weights correctly
|
|
0
|
11
|
August 11, 2024
|
Is fuse_fx supposed to preceed convert_fx in the quant pipeline?
|
|
1
|
21
|
August 9, 2024
|
Simple quantisation reproduction - how to convert state dict to int8
|
|
0
|
19
|
July 19, 2024
|
How to adjust the model to eliminate errors in convert_fx()?
|
|
10
|
181
|
July 18, 2024
|
Relationship between GPU Memory Usage and Batch Size
|
|
8
|
7094
|
July 17, 2024
|
Question about QAT quantization with torch.fx
|
|
7
|
109
|
July 16, 2024
|
Changing Qconfig to set datatype to int8
|
|
0
|
54
|
July 5, 2024
|
Fusing a QAT model post-training
|
|
4
|
127
|
July 2, 2024
|
Relative error greater than unit roundoff for torch.float16
|
|
1
|
82
|
July 2, 2024
|
QuantStub with values in [-128,127]
|
|
6
|
673
|
July 2, 2024
|
TypeError: quantized_add() missing 2 required positional arguments: 'op_scale' and 'op_zero_point'
|
|
8
|
946
|
July 2, 2024
|
Pytorch quantized model to ONNX - quantized_decomposed::quantize_per_tensor Error
|
|
3
|
128
|
July 2, 2024
|
After the neural network is quantized, how to use the GPU to infer the model?
|
|
1
|
132
|
June 28, 2024
|
Input data range after quantization
|
|
1
|
117
|
June 28, 2024
|
Quantizer Backend for Linear Op intermittent failures (ExecuTorch)
|
|
6
|
199
|
June 28, 2024
|
Random quantization
|
|
1
|
105
|
June 15, 2024
|