mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-17 21:10:43 +00:00
3fa73a5b6a
* cancel night build on pyop * add rewriter to rewrite cpu provider * skip BuildKernelCreateInfo<void> * refactor variable name and comment * include ops from csv file * process multiple eps * add default function to cuda provider * rename function and add license header * fix import * add doc * fix typo * deal with empty kernel entry in cuda * rename the rewriter file * add comment into provider file * add comment and rename function * log warnings * refactor extracting logic * add entry for script to run solo * add better example * avoid onnx importing * fix flake8 alerts * minor fixes to better comments and doc * add entries for all domains * add void entry into contrib providers * format cuda_contrib_kernels.cc * format cpu_contrib_kernels.cc * add all providers * add default entry to all providers * include op_kernel header * cancelling change in providers beyond cpu/cuda * rename file and switch file format to domain;opset;op1,op2... * update doc * restore non-regular ending grammar in cuda_contrib_kernels.cc * add ort_root as input argument of script * enable test in ci * update doc * update doc * revert change on linux gnu ci * switch to set to host ops * simplify trimming logic * add domain map to track current model * allow ort_root to take relative path
1.1 KiB
1.1 KiB
Reduce binary size
To reduce compiled binary size, two options are available:
- --include_ops_by_model=<path to directory of models>
- --include_ops_by_file=<path to a file>
The options empower building to comment out operators listed in execution provider(s), thereby downsizing the output.
include_ops_by_model
The argument enables the compile binary of including only operators consumed by models in the specified directory.
include_ops_by_file
The argument enables the compiled binary of including only operators referred. The file has format like:
#domain;opset;op1,op2...
ai.onnx;1;MemcpyToHost,MemcpyFromHost
ai.onnx;11;Gemm
More usage tips
- By default, the trimming happens only on cpu execution provider, with --use_cuda it will also be applied to cuda;
- If both are specified, operators referred from either argument will be kept active;
- The script is located under toos/ci_build/, and could go solo to apply to cpu and cuda providers as:
python exclude_unused_ops.py --model_path d:\ReduceSize\models --file_path d:\ReduceSize\ops.txt --ort_root d:\onnxruntime