MegCC icon indicating copy to clipboard operation
MegCC copied to clipboard

MegCC是一个运行时超轻量,高效,移植简单的深度学习模型编译器

Results 10 MegCC issues
Sort by recently updated
recently updated
newest added

tensor_c.h里面 LITE_API int LITE_make_tensor(const LiteTensorDesc tensor_describe, LiteTensor* tensor); 在 tensor.c未找到实现,请问下目前版本是不支持吗?

报这个错误 2023/08/25 15:43:04 - DEBUG - cmake build: cd /home/work/wanxin/megcc_root_release/release_megcc/yolox_example/kernel_yolox_s_arm_v2/runtime && ninja install/strip ninja: error: '/home/work/wanxin/megcc_root_release/release_megcc/runtime/version.ld', needed by 'libTinyNN.so', missing and no known rule to make it Traceback (most recent...

build target 为 aarch64 的 linux ,按照 https://github.com/MegEngine/MegCC/blob/main/yolox_example/README.md 中的说明操作,当执行 `python ../runtime/scripts/runtime_build.py --cross_build --kernel_dir ./kernel_yolox_s_arm/ --remove_old_build --cross_build_target_os LINUX --cross_build_target_arch aarch64` 时,会出现如下错误: ```bash /home/xxxx/Downloads/megcc_release/release_megcc/runtime/../immigration/include/marm_neon.h:241:62: error: pragma or attribute ‘target("dotprod")’ is not valid...

dump代码如下 @jit.trace(symbolic=True, capture_as_const=True) def fun(data, *, net): pred = net(data) return pred fun(data, net=model) fun.dump("test.mge", arg_names=["data"],optimize_for_inference=False, enable_fuse_conv_bias_nonlinearity=False, enable_fuse_conv_bias_with_z=False)

hi I get the latest source code, I build megcc source code as the user guide, the step as follows: 1. apt-get install cmake ninja-build 2./third_party/prepare.sh 3. cd megcc/compiler 4....

Hi, Good Job! How can I find the code part about RISC-V ? Thanks,

目前MegEngine只支持了MegEngine的模型编译,用户只能使用MegEngine模型进行编译,onnx需要转换到MegEngine,考虑直接支持torchscript模型

./third_party/prepare.sh 编译的时候遇到错误:../dnn/test/fallback/gi.cpp:38:33: error: ‘isnan’ was not declared in this scope, and no declarations were found by argument-dependent lookup at the point of instantiation [-fpermissive]

是否会有模型在不同硬件的性能benckmark