- Sort Score
- Result 10 results
- Languages All
Results 1 - 3 of 3 for unpack_quantized_types_ (0.18 sec)
-
tensorflow/compiler/mlir/quantization/stablehlo/passes/testing/test_post_calibration_component.cc
config.mutable_static_range_ptq_preset(); const QuantizationConfig new_config = ExpandPresets(config); PipelineConfig pipeline_config; pipeline_config.set_unpack_quantized_types(unpack_quantized_types_); PostCalibrationComponent component(&ctx); component.AddPasses(pm, new_config.specs(), pipeline_config); if (failed(runPipeline(pm, module_op))) { signalPassFailure(); } }
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Apr 15 12:53:33 UTC 2024 - 3.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/passes/testing/passes.td
let summary = "Test-only pass to test the PostCalibrationComponent."; let description = [{ Runs the post-calibration passes for post-training quantization. }]; let options = [ Option<"unpack_quantized_types_", "unpack-quantized-types", "bool", /*default=*/"true", "Unpacks ops with uniform quantized types into " "operations without uniform quantized types (mostly i8 or i32)."> ]; let dependentDialects = [
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 28 23:21:42 UTC 2024 - 4.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/cc/pass_pipeline.cc
pm.addPass(createQuantizeCompositeFunctionsPass(options)); // Add an inliner pass to inline quantized StableHLO functions. pm.addPass(createInlinerPass()); if (pipeline_config.unpack_quantized_types()) { AddStablehloQuantToIntPasses(pm); } } void AddWeightOnlyQuantizationPasses( OpPassManager& pm, const QuantizationSpecs& quantization_specs, const PipelineConfig& pipeline_config,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 10 04:07:09 UTC 2024 - 8.1K bytes - Viewed (0)