neural_compressor.ux.components.benchmark.execute_benchmark

Execute benchmark.

Module Contents

Functions

execute_benchmark(→ None)	Execute benchmark.
benchmark_result_update(→ dict)	Update benchmark result. (TF, ONNX models).
benchmark_result_update_pytorch_script(→ dict)	Update benchmark result. (PyTorch scripted models).
pytorch_script_bench_optimizations(→ float)	Benchmark for PyTorch scripted models (on the optimizations).
pytorch_script_bench_original_model(→ float)	Benchmark for PyTorch scripted models (on the original model).
execute_real_benchmark(→ dict)	Execute benchmark.

neural_compressor.ux.components.benchmark.execute_benchmark.execute_benchmark(data: Dict[str, Any]) → None

Execute benchmark.

Expected data: {

“request_id”: “asd”, “benchmark_id”: “1”

}

neural_compressor.ux.components.benchmark.execute_benchmark.benchmark_result_update(benchmark: Any, logs: Any, executor: Any, request_id: Any) → dict

Update benchmark result. (TF, ONNX models).

neural_compressor.ux.components.benchmark.execute_benchmark.benchmark_result_update_pytorch_script(benchmark: Any, request_id: Any, neural_coder_performance: Any, neural_coder_time: float) → dict

Update benchmark result. (PyTorch scripted models).

neural_compressor.ux.components.benchmark.execute_benchmark.pytorch_script_bench_optimizations(benchmark: Any, command_line_of_script: str, logs: Any) → float

Benchmark for PyTorch scripted models (on the optimizations).

neural_compressor.ux.components.benchmark.execute_benchmark.pytorch_script_bench_original_model(benchmark: Any, command_line_of_script: str, logs: Any) → float

Benchmark for PyTorch scripted models (on the original model).

neural_compressor.ux.components.benchmark.execute_benchmark.execute_real_benchmark(request_id: str, project_details: dict, benchmark_details: dict) → dict

Execute benchmark.