|
How to do qat after ptq in PyTorch2 quantization?
|
|
1
|
199
|
April 25, 2025
|
|
Switch loss function causes "RuntimeError: Found dtype Double but expected Float"
|
|
6
|
1931
|
April 24, 2025
|
|
How to quantize my torchscript to fp8
|
|
1
|
445
|
April 18, 2025
|
|
Loss stuck at quantization aware training for 16bits
|
|
1
|
85
|
April 18, 2025
|
|
Question about quantized model save & load
|
|
5
|
263
|
April 18, 2025
|
|
Quantization method diff between fake quant and true quant
|
|
1
|
127
|
April 14, 2025
|
|
Right way to insert QuantStub and DeQuantStub in eager mode quantization
|
|
6
|
272
|
April 12, 2025
|
|
QAT model is not performing as expected when compared to the original model
|
|
7
|
266
|
April 9, 2025
|
|
Can't get dynamic shape with torch.export.export_for_training
|
|
3
|
438
|
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
|
114
|
April 6, 2025
|
|
How to custom a quantizar using fx
|
|
1
|
80
|
April 6, 2025
|
|
Question on quantize_per_channel and dequantize
|
|
5
|
259
|
April 6, 2025
|
|
Quantized LLM inference vs quantized matrix multiplication speed in CPU
|
|
2
|
170
|
April 6, 2025
|
|
Quantization fails for custom backend
|
|
3
|
305
|
March 21, 2025
|
|
Simulating quantization to lower bit precision with quant_min/max setting on fused modules
|
|
0
|
97
|
March 19, 2025
|
|
Help Needed: High Inference Time & CPU Usage in VGG19 QAT model vs. Baseline
|
|
0
|
81
|
March 15, 2025
|
|
Is dynamic quantization in fact doing weight dequant instead of activation quant for `quantize_dynamic()`
|
|
1
|
169
|
March 13, 2025
|
|
Trying to Understand the Scale Computation During Static Quantisation
|
|
0
|
102
|
March 2, 2025
|
|
Exclude specific layers from quantization
|
|
1
|
180
|
February 24, 2025
|
|
Questions on QAT for Wav2Vec
|
|
3
|
329
|
February 24, 2025
|
|
"Deploy Quantized Models using Torch-TensorRT" failed
|
|
5
|
436
|
February 18, 2025
|
|
Additional layer in the conv weight after quantization
|
|
1
|
313
|
February 15, 2025
|
|
Compatibility Issue: Wav2Vec2 QAT with PyTorch 2 Export
|
|
1
|
224
|
February 13, 2025
|
|
Quantized::linear (xnnpack): xnn create operator failed(2)
|
|
1
|
209
|
February 12, 2025
|
|
JIT model is a deployment model or a quantized model?
|
|
0
|
87
|
February 7, 2025
|
|
How to customize a quantization algorithm and deploy it?
|
|
2
|
131
|
February 5, 2025
|
|
USing Quantization tutorial,but the result different
|
|
2
|
128
|
February 4, 2025
|
|
Data types on quantized models
|
|
0
|
172
|
February 4, 2025
|
|
Custom weight observer for powers of 2
|
|
2
|
916
|
January 29, 2025
|
|
Run quantized model on GPU
|
|
2
|
2479
|
January 23, 2025
|