-
# Model Request
### Which model would you like to see in the model zoo?
A quantized MobileNet (doesn't matter which version) could be fine. TensorFlow has published end to end quantized [MobileNet…
-
Hello,
I would like to train my model in a QAT scenario.
But from what I understand, during QAT, only the Forward pass calculations are done in quantized mode, whereas the weights that are saved are…
-
### 🐛 Describe the bug
The strange thing is that when I train only 100 epochs with FP32, the model can quantize normally, when I train 200 or more epochs and then try to do the quantization - the mod…
-
### OpenVINO Version
2024.0.0 - Current
### Operating System
Windows 10 Professional 2004 [Version 10.0.19041.1415]
### Device used for inference
CPU (Intel Xeon E-2288G CPU [Coffee Lak…
-
Hi:
I tried QAT on a model and exported the encodings. Then, I used the qnn-onnx-converter with --quantization_overrides and --input_list trying to put min/max/scale value after QAT into the converte…
-
## Description
trt10.5 pytorch-quantization has compile bug.
https://github.com/NVIDIA/TensorRT/blob/release/10.5/tools/pytorch-quantization/src/tensor_quant_gpu.cu#L28-L37
define two macro `AT_DI…
-
-
`python scripts/txt2img.py --prompt "a photograph of a huge bear, style of TIME magazine" --plms
/home/grayson/miniconda3/envs/ldm/lib/python3.8/site-packages/torchvision/io/image.py:13: UserWarning…
-
### Your current environment
```text
PyTorch version: 2.1.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Microsoft Windows 11 Home
GCC vers…
-
I tried quantizing Mamba using HuggingFace/Quanto and ran into the problem of perplexity for `lambada_openai` blowing up (> 1e^37) at lower quantization levels, even though other tasks retained their …