-
Hi, when I run `bash tool/run.sh`, assertion error below raises.
```shell
Assert failed 💀. weight_scales_.size() == bias.numel in file src/spconv/engine.cu:993, message: Invalid weight scales 1 !=…
-
### Issue Type
Bug
### Source
source
### MCT Version
Main
### OS Platform and Distribution
Ubuntu 20.04
### Python version
3.11
### Describe the issue
```shell
Using the quick start, GPTQ a…
-
### 💡 Your Question
The notebooks:
https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/qat_ptq_yolo_nas.md
https://github.com/Deci-AI/super-gradients/blob/master/documentati…
-
**Problem**
Inference is a tad bit slow when it comes to large datasets.
**Solution**
Performance gains can be achieved by using Intel's Neural Compressor: https://github.com/intel/neural-comp…
-
## 背景
飞桨官网的 API 文档，有中文和英文两个版本，都存储于 GitHub 中，并通过技术手段转为 HTML 文件后呈现在官网。
* `中文 API 文档`存储于 docs 仓库下，具体路径为 [PaddlePaddle/docs/docs/api/paddle](https://github.com/PaddlePaddle/docs/tree/develop/docs/api/padd…
-
My program stuck in here
How can I skip PTQ and export SCN onnx directly,
-
### Before Asking
- [X] I have read the [README](https://github.com/meituan/YOLOv6/blob/main/README.md) carefully. 我已经仔细阅读了README上的操作指引。
- [X] I want to train my custom dataset, and I have read the …
-
### System Info
When I use `device_map = "auto"` for LLaMA model on more than 3 H800 GPUs, errors pop up during model inference. But when I use fewer than 3 H800 GPUs, everything is OK. It seems to …
-
command ：
`python scripts/txt2img.py --prompt "a puppet wearing a hat" --plms --cond --ptq --weight_bit 4 --quant_mode qdiff --no_grad_ckpt --split --n_samples 5 --quant_act --act_bit 8 --sm_abit 16…
-
环境:
PaddleDetection 2.5
PaddleSlim 2.3.4
ubuntu 20.04
cuda 11.1
用PaddleDetection训练solov2，之后导出模型，导出命令如下
python tools/export_model.py -c configs/solov2/solov2_r50_enhance_symhua_coco.yml --output_…