|
About the quantization category
|
|
0
|
2552
|
October 2, 2019
|
|
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
|
|
3
|
11
|
February 7, 2026
|
|
[ROCm][CI] fp8 acceptable accuracy threshold
|
|
0
|
10
|
February 6, 2026
|
|
Extracting int8 weights and other quant params after convert_pt2e
|
|
0
|
14
|
February 3, 2026
|
|
XNNPACKQuantizer.set_module_name() not working as expected
|
|
1
|
28
|
February 1, 2026
|
|
Limitations of Int8 QAT for Linear Layers
|
|
0
|
19
|
January 29, 2026
|
|
Huge accuracy drop from QAT model after convert_pt2e
|
|
1
|
43
|
January 27, 2026
|
|
Variable-bit (sub 8-bits) quantization for custom hardware deployment with power-of-two (pot) scales
|
|
10
|
1476
|
January 6, 2026
|
|
Ost Training Quantization fails on SPAN model with type_as
|
|
1
|
38
|
December 4, 2025
|
|
Difference of IntxWeightOnlyConfig/UIntxWeightOnlyConfig/Int8WeightOnlyConfig/Int4WeightOnlyConfig/
|
|
2
|
55
|
December 4, 2025
|
|
Quantize convolution layer
|
|
1
|
52
|
December 4, 2025
|
|
PT2E quantization doesn't reduce the model size
|
|
2
|
96
|
December 4, 2025
|
|
How to use quantized weights for manual implementation of the model in FPGA?
|
|
2
|
1091
|
September 28, 2025
|
|
[pt2e][quant] Quantization of operators with multiple outputs (RNN, LSTM)
|
|
4
|
318
|
September 15, 2025
|
|
GPU MEM% allocation vs batch size and temporal dimension
|
|
3
|
97
|
September 13, 2025
|
|
TorchAO Migration
|
|
0
|
85
|
September 11, 2025
|
|
Does export support quantized models with torchAo
|
|
1
|
83
|
September 11, 2025
|
|
Should I perform quantization after activation functions like sigmoid and SiLU?
|
|
0
|
78
|
September 9, 2025
|
|
Quantization of Hybrid Pytorch Model
|
|
0
|
57
|
September 8, 2025
|
|
Error while converting quantized Torch model to ONNX
|
|
0
|
85
|
September 5, 2025
|
|
My model is taking too much time in calculating FFT to find top k
|
|
1
|
74
|
September 2, 2025
|
|
FX mode static_quantization for YOLOv7
|
|
16
|
1026
|
August 4, 2025
|
|
Could not run 'aten::quantize_per_tensor' with arguments from the 'QuantizedCPU' backend
|
|
7
|
4270
|
July 17, 2025
|
|
RuntimeError: quantized::conv2d_prepack() is missing value for argument 'stride'
|
|
1
|
70
|
July 1, 2025
|
|
Why is there such a significant difference between floating-point convolution and quantized integer convolution results?
|
|
2
|
78
|
June 30, 2025
|
|
[MPS] When device='mps', aten.linear.default op is not decomposed
|
|
1
|
77
|
June 5, 2025
|
|
Logits mismatch between PyTorch inference and manual implementation
|
|
1
|
115
|
April 29, 2025
|
|
QAT model drops accuracy after converting with torch.ao.quantization.convert
|
|
1
|
116
|
April 29, 2025
|
|
Qint8 Activations in PyTorch
|
|
1
|
247
|
April 25, 2025
|
|
How to do qat after ptq in PyTorch2 quantization?
|
|
1
|
170
|
April 25, 2025
|