|
About the quantization category
|
|
0
|
2431
|
October 2, 2019
|
|
Run quantized model on GPU
|
|
2
|
1413
|
January 23, 2025
|
|
Quantization of depthwise 1d convolution with QAT is slower than non-quantized
|
|
2
|
32
|
January 23, 2025
|
|
Taylor-series Approximation for Sigmiod in Integer
|
|
1
|
38
|
January 15, 2025
|
|
Triton kernel to efficiently dequantize int4
|
|
0
|
39
|
January 5, 2025
|
|
BatchNorm not fusing with Cone and ReLU
|
|
0
|
13
|
December 26, 2024
|
|
Compile Model with TensorRT
|
|
0
|
32
|
December 25, 2024
|
|
How to convert a QAT model to ONNX model
|
|
3
|
100
|
December 19, 2024
|
|
Pytorch 2 Export QAT is training
|
|
0
|
62
|
December 19, 2024
|
|
Quantized GLU not implemented?
|
|
1
|
64
|
December 17, 2024
|
|
Kernel Dies When Testing a Quantized ResNet101 Model in PyTorch
|
|
2
|
19
|
December 12, 2024
|
|
Auto-cast and pytorch 2 export quantization
|
|
8
|
194
|
December 9, 2024
|
|
RuntimeError: Quantized cudnn conv2d is currenty limited to groups = 1; received groups =16 , during QAT
|
|
3
|
839
|
December 6, 2024
|
|
Quantization fails for custom backend
|
|
2
|
74
|
December 6, 2024
|
|
Support for quantization in int16
|
|
5
|
69
|
December 5, 2024
|
|
Quantize a single tensor obtained from a float32 model
|
|
2
|
36
|
November 29, 2024
|
|
Can't get dynamic shape with torch.export.export_for_training
|
|
1
|
48
|
November 28, 2024
|
|
Simple quantisation reproduction - how to convert state dict to int8
|
|
1
|
36
|
November 27, 2024
|
|
torch.ao.nn.quantizable.modules.activation.MultiheadAttention not loading the pre-trained model weights correctly
|
|
1
|
31
|
November 27, 2024
|
|
QConfig for Resnet50 with weights dtype quint8
|
|
5
|
102
|
November 27, 2024
|
|
Load custom trained parameters into quantized model
|
|
1
|
28
|
November 27, 2024
|
|
Per channel setting for QAT Quantization
|
|
1
|
24
|
November 27, 2024
|
|
Custom QAT using ao.nn.qat modules, is this a valid approach?
|
|
1
|
23
|
November 27, 2024
|
|
Absence of qint32 in torch.ao.quantization.utils.weight_is_quantized
|
|
1
|
70
|
November 27, 2024
|
|
Questions on QAT for Wav2Vec
|
|
1
|
88
|
November 27, 2024
|
|
QAT QuantizedConv2d converted to ONNX format
|
|
1
|
67
|
November 27, 2024
|
|
Changing Qconfig to set datatype to int8
|
|
1
|
130
|
November 20, 2024
|
|
Inserting Unnecessary Fake Quants during QAT?
|
|
2
|
92
|
November 12, 2024
|
|
Torch.bfloat16 < how does it work? in bf 16 model
|
|
1
|
120
|
November 4, 2024
|
|
pytorch quantized linear function gives shape invalid error
|
|
3
|
78
|
November 1, 2024
|