-
When executing this line of code: `resume_cali_model(qnn, args.cali_ckpt, cali_data, args.quant_act, "qdiff", cond=False)`, the model cannot be loaded properly when running `qnn.load_state_dict(ckpt, …
-
When I QAT model in VitisAI3.0 env, I met a annoying print info:
I check the source …
-
## Description
When I do PTQ for model.onnx and build an engine, I think the `calib scales` are pulled in operation(mul with weights) , take no account of fusions and layout transform, for int8…
-
Is there a simple way to take a pre-trained model (e.g YOLO, BERT etc) and replace any Conv/Linear layers with QuantConv/QuantLinear? Perhaps with setattr?
Thanks
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
- TensorFlow installed from (source or binary):
- TensorFlow version (or github SHA if from source):
**Provide…
-
I have tried [this official example of Smooth quant alpha auto tuning](https://github.com/intel/neural-compressor/tree/master/examples/pytorch/nlp/huggingface_models/language-modeling/quantization/ptq…
-
嗨 大家好，
我想得到使用TensorRT量化方式进行量化后，能够达到MQBench官方精度的resnet50网络
但是我没有找到（如果您有量化后的网络，并能够分享给我，我不胜感激）
为此，我按照官方提供的步骤进行处理
```
Clone and install MQBench;
Prepare the ImageNet dataset from [the offi…
-
**Is your feature request related to a problem? Please describe.**
I currently have an FX workflow, but to use PTQ I need to also get my models to compile with TS, and it's hard to maintain compatibi…
-
I follow this [https://github.com/NVIDIA/TensorRT/blob/release/8.6/quickstart/quantization_tutorial/qat-ptq-workflow.ipynb](url) converted q_model() to onnx format, I want use python api convert onnx …
-
### bug描述 Describe the Bug
### 错误信息
错误引入 PR：https://github.com/PaddlePaddle/Paddle/pull/50915
case 地址：https://github.com/PaddlePaddle/PaddleTest/tree/develop/inference/python_api_test/test_nlp_…