|
About the quantization category
|
|
0
|
2447
|
October 2, 2019
|
|
"Deploy Quantized Models using Torch-TensorRT" failed
|
|
5
|
51
|
February 18, 2025
|
|
Additional layer in the conv weight after quantization
|
|
1
|
222
|
February 15, 2025
|
|
Questions on QAT for Wav2Vec
|
|
2
|
134
|
February 14, 2025
|
|
Compatibility Issue: Wav2Vec2 QAT with PyTorch 2 Export
|
|
1
|
65
|
February 13, 2025
|
|
Quantized::linear (xnnpack): xnn create operator failed(2)
|
|
1
|
24
|
February 12, 2025
|
|
JIT model is a deployment model or a quantized model?
|
|
0
|
23
|
February 7, 2025
|
|
How to customize a quantization algorithm and deploy it?
|
|
2
|
27
|
February 5, 2025
|
|
USing Quantization tutorial,but the result different
|
|
2
|
28
|
February 4, 2025
|
|
Data types on quantized models
|
|
0
|
55
|
February 4, 2025
|
|
Custom weight observer for powers of 2
|
|
2
|
674
|
January 29, 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
|
|
0
|
11
|
January 26, 2025
|
|
Run quantized model on GPU
|
|
2
|
1580
|
January 23, 2025
|
|
Quantization of depthwise 1d convolution with QAT is slower than non-quantized
|
|
2
|
102
|
January 23, 2025
|
|
Taylor-series Approximation for Sigmiod in Integer
|
|
1
|
76
|
January 15, 2025
|
|
Triton kernel to efficiently dequantize int4
|
|
0
|
86
|
January 5, 2025
|
|
BatchNorm not fusing with Cone and ReLU
|
|
0
|
17
|
December 26, 2024
|
|
Compile Model with TensorRT
|
|
0
|
48
|
December 25, 2024
|
|
How to convert a QAT model to ONNX model
|
|
3
|
138
|
December 19, 2024
|
|
Pytorch 2 Export QAT is training
|
|
0
|
83
|
December 19, 2024
|
|
Quantized GLU not implemented?
|
|
1
|
103
|
December 17, 2024
|
|
Kernel Dies When Testing a Quantized ResNet101 Model in PyTorch
|
|
2
|
24
|
December 12, 2024
|
|
Auto-cast and pytorch 2 export quantization
|
|
8
|
285
|
December 9, 2024
|
|
RuntimeError: Quantized cudnn conv2d is currenty limited to groups = 1; received groups =16 , during QAT
|
|
3
|
880
|
December 6, 2024
|
|
Quantization fails for custom backend
|
|
2
|
107
|
December 6, 2024
|
|
Support for quantization in int16
|
|
5
|
84
|
December 5, 2024
|
|
Quantize a single tensor obtained from a float32 model
|
|
2
|
45
|
November 29, 2024
|
|
Can't get dynamic shape with torch.export.export_for_training
|
|
1
|
71
|
November 28, 2024
|
|
Simple quantisation reproduction - how to convert state dict to int8
|
|
1
|
47
|
November 27, 2024
|
|
torch.ao.nn.quantizable.modules.activation.MultiheadAttention not loading the pre-trained model weights correctly
|
|
1
|
39
|
November 27, 2024
|