-
Hi，
1 请问下 TinyPose模型的自动化压缩代码无bug版本的整理好了吗？
2 是否有文档，确保过程无误？
3 coco数据集qat全量化后掉点多少，业务最终掉点多少呢？
多谢
-
## Bug Description
I'm trying to apply quantization aware training(QAT) procedure to ViT model
Using this example notebook: https://github.com/pytorch/TensorRT/blob/main/notebooks/qat-ptq-workflo…
-
> 你好像需要这个？ https://github.com/openppl-public/ppq/tree/master/ppq/samples/TensorRT
作者你好，这个生成engine的 lenet_int8.cpp，好像是通过下图的方式利用tensorrt c++ 的api一步一步搭建的engine，是否有利用c++ trt.OnnxParser的方式…
-
## 背景
众所周知，Paddle 是一个历史悠久的框架，使得 Paddle 能够久经考验，应对各种场景稳定运行。但历史的沉淀同样带来一个严重的问题，就是框架内 API 语义不清晰，多种 API 能够做同样或者类似的事情。得益于我们的公开 API 审查机制和 fluid 清理，公开 API 中类似问题较少，但框架内部仍存在大量历史遗留的内部 API 的使用，这些 API 的存在导致框架内部需…
-
### 🚀 The feature, motivation and pitch
There are situations such as ablation studies, custom fusion implementations and debugging that would benefit from disabling PyTorch fusion during quantizati…
-
Hi,
I am trying to reproduce the results in the paper for stable diffusion. and use the sdv1.4 ckpt and sd_w4a8_ckpt.pth for ptq using NVIDIA V100
My command is like the following:
python scripts…
-
### Issue Type
Bug
### Source
pip (model-compression-toolkit)
### MCT Version
1.8.0
### OS Platform and Distribution
Ubuntu 20.04
### Python version
3.8.10
### Describe t…
-
```
---------------------------------------------------------------------------
ImportError Traceback (most recent call last)
[](https://localhost:8080/#) in ()
…
-
[27.07.2023 12:17:29] jasiu-rozowyczlowiek
-
### What happened?
When running first OnnxQuantization pass with default parameters and a pass then with QUInt weight and activation type, the model parameters are not quantized to QUInt.
To clarif…