-
I'm following the steps exactly as detailed in the README.md. When reaching the quantization step, the line
```
python3 qat.py quantize --weights yolov9-c-converted.pt --name yolov9_qat --exist-…
-
Status: Draft
Updated: 06/17/2024
# Objective
In this doc we’ll talk about Tensor subclass based quantization API for modeling users and developers.
# Modeling User API
Modeling users refer t…
-
### 🚀 The feature, motivation and pitch
Quantized Inference on GPU
### Additional context
Quantization support for GPU inference is an area of active development with two existing protypes
…
-
Previously we do this
```python
from torchao.quantization.quant_api import change_linear_weights_to_int8_woqtensors
model = torch.compile(model, mode="max-autotune", fullgraph=True)
change_lin…
-
@Chris-Schnaufer a few things to finish up the production BETYdb at UA:
* [x] Set the primary keys to 9 billion range
* create a .env file where you launched pecan from and add `BETY_LOCAL_SERVE…
-
Hello, I have installed and configured `pyttsx3` on my macOS. And by default it uses `nsss` as driver and this setting works fine. However when I change the driver to `espeak` I'm unable to get any so…
-
root@90e0df0b7943:/home/TensorRT/parsers/onnx/build# ./onnx2trt /home/my.onnx -o my.trt
Input filename: /home/my.onnx
ONNX IR version: 0.0.6
Opset version: 12
Producer name: pytorch
Producer vers…
-
![97a28be8c620c758793f3d99cb0240d](https://user-images.githubusercontent.com/47705677/186617810-c9c3d4a3-49d1-43cb-9055-3b92226c7ce3.png)
-
**Describe the bug**
As Ubuntu hwe kernel updated from 6.5.0-35 to 6.5.0-41, DSA e2e started to fail. The failure seems to be related to a change in the kernel where (due to a security issue) access …
-
### 🐛 Describe the bug
Torchbench has some models failed on accuracy check, the detail model list can be found as below table.
precision | mode | model
-- | -- | --
bfloat16 | inference | pytorc…