We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
使用最新的代码,在windows上使用 call "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build\vcvars64.bat" cmake -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DMNN_BUILD_LLM=ON -DMNN_SUPPORT_TRANSFORMER_FUSE=ON -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true .. ninja -j8
构建的exe,加载的模型是MNN官方提供的Qwen3-0.6B-MNN,命令行执行结果: $ ./llm_demo.exe ../../Qwen3-0.6B-MNN/config.json The device supports: i8sdot:0, fp16:0, i8mm: 0, sve2: 0, sme2: 0 config path is ../../Qwen3-0.6B-MNN/config.json main, 227, cost time: 7952.845215 ms Prepare for tuning opt Begin Segmentation fault
同样的代码,在ubuntu22.04上编译能正常使用,这是为什么呢?
The text was updated successfully, but these errors were encountered:
MNN 是什么时候的版本? 在 llm_demo 里面打印一下 MNN 的version 看下,有可能系统库里有 mnn 冲突了。
Sorry, something went wrong.
No branches or pull requests
使用最新的代码,在windows上使用
call "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build\vcvars64.bat"
cmake -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DMNN_BUILD_LLM=ON -DMNN_SUPPORT_TRANSFORMER_FUSE=ON -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true ..
ninja -j8
构建的exe,加载的模型是MNN官方提供的Qwen3-0.6B-MNN,命令行执行结果:
$ ./llm_demo.exe ../../Qwen3-0.6B-MNN/config.json
The device supports: i8sdot:0, fp16:0, i8mm: 0, sve2: 0, sme2: 0
config path is ../../Qwen3-0.6B-MNN/config.json
main, 227, cost time: 7952.845215 ms
Prepare for tuning opt Begin
Segmentation fault
同样的代码,在ubuntu22.04上编译能正常使用,这是为什么呢?
The text was updated successfully, but these errors were encountered: