- Sort Score
- Result 10 results
- Languages All
Results 1 - 2 of 2 for enable_weight_only_quantization_ (0.46 sec)
-
tensorflow/compiler/mlir/lite/transforms/quantize.cc
enable_whole_model_verify_ = quant_specs.whole_model_verify; enable_legacy_quantize_ = quant_specs.legacy_float_scale; enable_dynamic_range_quantization_ = quant_specs.weight_quantization; enable_weight_only_quantization_ = quant_specs.weight_only_quantization; } void runOnOperation() override; private: quant::QuantizationSpecs quant_specs; };
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 20:30:06 UTC 2024 - 13.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/transforms/passes.td
Option<"enable_dynamic_range_quantization_", "enable-dynamic-range-quantization", "bool", "false", "Whether run post-training dynamic range quantization pass">, Option<"enable_weight_only_quantization_", "enable-weight-only-quantization", "bool", "false", "Whether to run weight-only for post-training dynamic range quantization pass">,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Apr 24 20:30:06 UTC 2024 - 22.6K bytes - Viewed (0)