wuxianjun666

cmake -G "MinGW Makefiles" -DGGML_CUBLAS=ON .. error in windows 10

2

GNU ld (GNU Binutils) 2.30 -- x86 detected -- Found CUDAToolkit: C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.6/include (found version "11.6.55") -- cuBLAS found -- The CUDA compiler identification is NVIDIA 11.6.55...

In lora.hpp， this code : struct ggml_context* ctx0 = ggml_init(params); init a ctx0, but I not found ggml_free(ctx0); I do not know ggml_free(ctx0) is necessary.

Can not release memory

7

in ggml_extend.hpp, the destructor function ~GGMLModule(), ~GGMLModule() noexcept(false){ LOG_DEBUG("BEGIN TO SUPER RELEASE ........."); free_params_buffer(); LOG_DEBUG("SUPER RELEASE FINISHED........."); } It always gets stuck here. because of this function: free_params_buffer(); there ara...

lora can not free memory

1

i added ~LoraModel() in lora.hpp,  The programme just keeps getting stuck here.

how to debug in vscode

Exporting the operator 'aten::fft_fft2' to ONNX opset version 19 is not supported.

训练文本行分类模型cls_mv3在转换main_export时报错

3

### 🔎 Search before asking - [x] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report. - [x] I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no...

paddle2onnx无法适配paddlepaddle-gpu=3.3版本

12

### 🔎 Search before asking - [x] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report. - [x] I have searched the PaddleOCR [Issues](https://github.com/PaddlePaddle/PaddleOCR/issues) and found no...

import paddle2onnx报错

2

此时的版本： paddle2onnx 2.0.2rc3 paddlepaddle-gpu 3.3.0.dev20251123 (cv128) PS E:\GitProjects\Python\ocr\K2DLOCRV10\Code\02InspectApp\PaddleOCRRTX5060> paddlex --paddle2onnx --paddle_model_dir .\output\rec --onnx_model_dir .\output\rec --opset_version 11 Input dir: output\rec Output dir: output\rec Paddle2ONNX conversion starting... Traceback (most recent call last):...