|
About the quantization category
|
|
0
|
2487
|
October 2, 2019
|
|
[pt2e][quant] Quantization of operators with multiple outputs (RNN, LSTM)
|
|
3
|
88
|
May 1, 2025
|
|
Logits mismatch between PyTorch inference and manual implementation
|
|
1
|
21
|
April 29, 2025
|
|
QAT model drops accuracy after converting with torch.ao.quantization.convert
|
|
1
|
16
|
April 29, 2025
|
|
Qint8 Activations in PyTorch
|
|
1
|
56
|
April 25, 2025
|
|
How to do qat after ptq in PyTorch2 quantization?
|
|
1
|
39
|
April 25, 2025
|
|
Switch loss function causes "RuntimeError: Found dtype Double but expected Float"
|
|
6
|
1710
|
April 24, 2025
|
|
How to quantize my torchscript to fp8
|
|
1
|
46
|
April 18, 2025
|
|
Loss stuck at quantization aware training for 16bits
|
|
1
|
19
|
April 18, 2025
|
|
Question about quantized model save & load
|
|
5
|
65
|
April 18, 2025
|
|
Quantization method diff between fake quant and true quant
|
|
1
|
17
|
April 14, 2025
|
|
Right way to insert QuantStub and DeQuantStub in eager mode quantization
|
|
6
|
65
|
April 12, 2025
|
|
QAT model is not performing as expected when compared to the original model
|
|
7
|
61
|
April 9, 2025
|
|
Can't get dynamic shape with torch.export.export_for_training
|
|
3
|
153
|
April 8, 2025
|
|
The code aims to collect data about SiLU (Sigmoid Linear Unit) activation layers in a quantized YOLOv5 model. Specifically, it: Creates a custom SiLUDataCollector to replace SiLU layers Captures quantization parameters (scale and zero point) Saves quanti
|
|
1
|
38
|
April 6, 2025
|
|
How to custom a quantizar using fx
|
|
1
|
26
|
April 6, 2025
|
|
Question on quantize_per_channel and dequantize
|
|
5
|
74
|
April 6, 2025
|
|
Quantized LLM inference vs quantized matrix multiplication speed in CPU
|
|
2
|
52
|
April 6, 2025
|
|
Quantization fails for custom backend
|
|
3
|
186
|
March 21, 2025
|
|
Simulating quantization to lower bit precision with quant_min/max setting on fused modules
|
|
0
|
20
|
March 19, 2025
|
|
Help Needed: High Inference Time & CPU Usage in VGG19 QAT model vs. Baseline
|
|
0
|
23
|
March 15, 2025
|
|
Is dynamic quantization in fact doing weight dequant instead of activation quant for `quantize_dynamic()`
|
|
1
|
45
|
March 13, 2025
|
|
Trying to Understand the Scale Computation During Static Quantisation
|
|
0
|
28
|
March 2, 2025
|
|
Exclude specific layers from quantization
|
|
1
|
63
|
February 24, 2025
|
|
Questions on QAT for Wav2Vec
|
|
3
|
203
|
February 24, 2025
|
|
"Deploy Quantized Models using Torch-TensorRT" failed
|
|
5
|
106
|
February 18, 2025
|
|
Additional layer in the conv weight after quantization
|
|
1
|
248
|
February 15, 2025
|
|
Compatibility Issue: Wav2Vec2 QAT with PyTorch 2 Export
|
|
1
|
109
|
February 13, 2025
|
|
Quantized::linear (xnnpack): xnn create operator failed(2)
|
|
1
|
106
|
February 12, 2025
|
|
JIT model is a deployment model or a quantized model?
|
|
0
|
31
|
February 7, 2025
|