|
About the quantization category
|
|
0
|
2585
|
October 2, 2019
|
|
Pytorch FX Quantization for custom models
|
|
0
|
103
|
August 25, 2026
|
|
Torchao get RuntimeError
|
|
0
|
78
|
April 15, 2026
|
|
XNNPACKQuantizer.set_module_name() not working as expected
|
|
3
|
179
|
March 5, 2026
|
|
[ROCm][CI] fp8 acceptable accuracy threshold
|
|
2
|
216
|
February 20, 2026
|
|
Extracting int8 weights and other quant params after convert_pt2e
|
|
1
|
158
|
February 17, 2026
|
|
Limitations of Int8 QAT for Linear Layers
|
|
1
|
155
|
February 17, 2026
|
|
Post training quantized model gets the error "Copying from quantized Tensor to non-quantized Tensor is not allowed" even though I'm not copying tensor
|
|
5
|
258
|
February 12, 2026
|
|
Huge accuracy drop from QAT model after convert_pt2e
|
|
1
|
175
|
January 27, 2026
|
|
Variable-bit (sub 8-bits) quantization for custom hardware deployment with power-of-two (pot) scales
|
|
10
|
1739
|
January 6, 2026
|
|
Ost Training Quantization fails on SPAN model with type_as
|
|
1
|
119
|
December 4, 2025
|
|
Difference of IntxWeightOnlyConfig/UIntxWeightOnlyConfig/Int8WeightOnlyConfig/Int4WeightOnlyConfig/
|
|
2
|
200
|
December 4, 2025
|
|
Quantize convolution layer
|
|
1
|
190
|
December 4, 2025
|
|
PT2E quantization doesn't reduce the model size
|
|
2
|
218
|
December 4, 2025
|
|
How to use quantized weights for manual implementation of the model in FPGA?
|
|
2
|
1206
|
September 28, 2025
|
|
[pt2e][quant] Quantization of operators with multiple outputs (RNN, LSTM)
|
|
4
|
507
|
September 15, 2025
|
|
GPU MEM% allocation vs batch size and temporal dimension
|
|
3
|
245
|
September 13, 2025
|
|
TorchAO Migration
|
|
0
|
144
|
September 11, 2025
|
|
Does export support quantized models with torchAo
|
|
1
|
179
|
September 11, 2025
|
|
Should I perform quantization after activation functions like sigmoid and SiLU?
|
|
0
|
153
|
September 9, 2025
|
|
Quantization of Hybrid Pytorch Model
|
|
0
|
110
|
September 8, 2025
|
|
Error while converting quantized Torch model to ONNX
|
|
0
|
166
|
September 5, 2025
|
|
My model is taking too much time in calculating FFT to find top k
|
|
1
|
147
|
September 2, 2025
|
|
FX mode static_quantization for YOLOv7
|
|
16
|
1247
|
August 4, 2025
|
|
Could not run 'aten::quantize_per_tensor' with arguments from the 'QuantizedCPU' backend
|
|
7
|
4369
|
July 17, 2025
|
|
RuntimeError: quantized::conv2d_prepack() is missing value for argument 'stride'
|
|
1
|
144
|
July 1, 2025
|
|
Why is there such a significant difference between floating-point convolution and quantized integer convolution results?
|
|
2
|
203
|
June 30, 2025
|
|
[MPS] When device='mps', aten.linear.default op is not decomposed
|
|
1
|
162
|
June 5, 2025
|
|
Logits mismatch between PyTorch inference and manual implementation
|
|
1
|
217
|
April 29, 2025
|
|
QAT model drops accuracy after converting with torch.ao.quantization.convert
|
|
1
|
211
|
April 29, 2025
|