-
Hi neuralmagic team !
Very nice work with AutoFP8 ! We were thinking of integrating AutoFP8 in transformers, so that users can run your checkpoints directly with transformers ! We would simply rep…
-
### 💡 Your Question
I used the [Roboflow notebook](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolo-nas-on-custom-dataset.ipynb?ref=blog.roboflow.com) to …
-
# PTQ | Visual Studio Code doesn't come up in the Windows 10 start bar search
Visual Studio Code doesn’t come up in the Windows 10 start bar search
[https://oclockvn.github.io/2020/12/18/vscode-does…
-
### Motivation
Hi~ I notice that only the TRT-PTQ method is supported in mmdeploy. Now I have a quantized ONNX model with QDQ nodes, or a float ONNX model and related calibration.cache file. How to d…
-
There's something wrong with my verification, could you give me some reference data?
My experiment is as follows:
1, ptq —> 2, qat —> 3, bn reestimation —> 4, fold_all_batch_norms_to_scale
afte…
-
Performing post training full integer quantisation of PyTorch developed model in TensorFlow framework throws following error
**PyTorch model -> ONNX model -> TensorFlow model -> TensorFlow PTQ Quan…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Current Behavior
我是用t4进行推理,它是支持int8和int4的
输入长度为1000,int4需要32s,fp16只需要12s
### Expected Behavior
_No respon…
-
Hi.
I have converted BEVFusion model from torch to onnx but it fails np.testing.allclose
```
Mismatched elements: 17068436 / 100663296 (17%)
Max absolute difference: 0.00343999
Max relative dif…
-
# PaddleSlim量化
![image](https://user-images.githubusercontent.com/1312389/170643197-8a42af2b-b696-4363-ac3a-29a582642162.png)
PaddleSlim主要包含三种量化方法:量化训练(Quant Aware Training, QAT)、动态离线量化(Post Train…
-
hi你好,我在使用ptq后得到了量化模型,我也开启了onnx_format,但在paddle2onnx的过程中遇到如下报错:
![image](https://user-images.githubusercontent.com/96160062/229083525-f8eb0bc9-02d3-4c00-9363-d0d194a3a504.png)
请问怎么才能让他生成对应的量化校准表呢,非常感…