pip install git+https://github.com/inisis/OnnxSlim@main Install From Local git clone https://github.com/inisis/OnnxSlim && cd OnnxSlim/ pip install . How to use onnxslim your_onnx_model slimmed_onnx_model For more usage, see onnxslim -h or refer to our examples Projects using...
pip install . How to use onnxslim your_onnx_model slimmed_onnx_model For more usage, see onnxslim -h or refer to our examples References onnx-graphsurgeon Polygraphy onnx-simplifier tabulate onnxruntime Contact Discord: https://discord.gg/nRw2Fd3VUS QQ Group: 873569894About...
To deliver the IntelliCode line completion experience at a low cost, we decided to deploy GPT-C on the client-side. This means that the GPT-C model needs to be run on CPU efficiently with a wide range of client devices. Thanks to ONNX Runtime, our first attempt ...
The execution time of theExtractor.extract_modelfunction is reduced from 7.24 seconds to 1.15 seconds. TheExtractor.extract_modelfunction is no longer the slowest part of the extract model process. check_model 3.31s infer_shapes 6.15s Extractor.extract_model 1.16s onnx.save 5.60s check_model 2.4...
auto model_proto = ONNX_NAMESPACE::ModelProto::Create(); auto graph_proto = model_proto->mutable_graph(); // create a graph model_proto->set_ir_version(ONNX_NAMESPACE::Version::IR_VERSION); for (const auto& op : original_graph.DomainToVersionMap()) { auto* opset_import = model_...
bin add executable Aug 24, 2023 docs update doc Mar 7, 2024 examples [Feature] add common_subexpression_elimination doc (#11) Mar 21, 2024 images [Feature] add common_subexpression_elimination doc (#11) Mar 21, 2024 onnxslim add args check (#27) ...
A Toolkit to Help Optimize Large Onnx Model. Contribute to nihui/OnnxSlim development by creating an account on GitHub.