ZhenLei Xu
ZhenLei Xu
some error in mlp_customdata_basic.ipynb, this tutorial is helping me study tensorflow,thanks!
When I run unit_tests/01_memory_read_write unit test, find these errors ```bash >>> python aiecc.py --sysroot=/ --aie-generate-xaiev2 ~/work/new-aie/mlir-aie/test/unit_tests/01_memory_read_write/aie.mlir -I/home/lay/work/new-aie/mlir-aie/runtime_lib /home/lay/work/new-aie/mlir-aie/runtime_lib/test_library.cpp ~/work/new-aie/mlir-aie/test/unit_tests/01_memory_read_write/test.cpp -o test.elf >>> ./test.elf .... MW: 0x20000072000, 0x2, 0x0 MW: 0x20000072008,...
## build error. Follow https://github.com/onnx/onnx-mlir/blob/main/docs/BuildOnLinuxOSX.md. LLVM： 59548fe873d8 ``` [9/40] Building CXX object src/Builder/CMakeFiles/OMBuilder.dir/FrontendDialectTransformer.cpp.o FAILED: src/Builder/CMakeFiles/OMBuilder.dir/FrontendDialectTransformer.cpp.o /usr/bin/c++ -DONNX_ML=1 -DONNX_MLIR_ENABLE_MHLO -DONNX_NAMESPACE=onnx -D_DEBUG -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS -D__STDC_LIMIT_MACROS -I/home/lay/soft/mlir/llvm-project/llvm/include -I/home/lay/soft/mlir/llvm-project/build/include -I/home/lay/soft/mlir/llvm-project/mlir/include -I/home/lay/soft/mlir/llvm-project/build/tools/mlir/include -I/home/lay/soft/mlir/onnx-mlir -I/home/lay/soft/mlir/onnx-mlir/build -I/home/lay/soft/mlir/onnx-mlir/include...
I lowing mnist.onnx to .mlir file. But some weights with blob format(I guess）， how to decode this string to matrix or list? ``` %0 = "krnl.global"() {name = "constant_0", shape...
When I run [mlir-aie](https://github.com/Xilinx/mlir-aie)/[test](https://github.com/Xilinx/mlir-aie/tree/main/test)/[unit_tests](https://github.com/Xilinx/mlir-aie/tree/main/test/unit_tests)/aievec_tests/, with following error ``` (py38) ➜ aievec_tests xchesscc -f -g +s -p me -P ${XILINX_VITIS}/aietools/data/aie_ml/lib/ +w work +o work -I. -I. testbench.cc kernel.cc Configuration: Release_LLVM Compiling...
mnist.mlir file in https://gist.github.com/HadXu/8987a2bca3e2a6400cc8c533b6d132c2 And this mlir can run with mlir-runner with success. ``` (py38) ➜ mnist-mlir mlir-opt mnist.mlir --lower-affine -convert-scf-to-cf -convert-linalg-to-llvm -convert-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | mlir-cpu-runner -O3 -e entry...
where the argument "-lhlo-legalize-to-linalg” of mlir-hlo-opt?
### Other 1. 如[K230_实战基础篇_hello_world.md](https://github.com/kendryte/k230_docs/blob/main/zh/02_applications/tutorials/K230_%E5%AE%9E%E6%88%98%E5%9F%BA%E7%A1%80%E7%AF%87_hello_world.md)所示，将代码编译后放到sdcard中 app下在大核中能够看到该可执行程序，可以直接执行。 2. 在大核中无法看到/sharefs文件夹  因此我只能将hello_world产生的文件放到sdcard的app中，在大核中去运行，小核无法看到。 固件为[CanMV-K230_micropython_v0.3_sdk_v1.1_nncase_v2.4.0.img.gz](https://kendryte-download.canaan-creative.com/developer/k230/CanMV-K230_micropython_v0.3_sdk_v1.1_nncase_v2.4.0.img.gz)
开始运行这个项目，提示数据库建立错误，原来是django版本错了，原来楼主用的1.8
Follow https://huggingface.co/docs/transformers/en/quantization/fbgemm_fp8 and I run it successfully. But when I run it with qwen2 model, with error "RuntimeError: Invalid datatype. input must be BF16".  --------------------------------------------------------------------------- RuntimeError Traceback (most recent...