- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for shouldKeepUnusedQdqPattern (0.29 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/passes/quantize.cc
return "Apply quantization on models in TensorFlow dialect"; } // Determine if the unused Q-DQ pairs need to be removed. For weight-only // quantizable ops, Q-DQ ops need to be preserved. bool shouldKeepUnusedQdqPattern(); void runOnOperation() override; private: QuantizationSpecs quant_specs_; Option<bool> weight_quantization_{ *this, "weight-quantization", llvm::cl::init(false),
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Mar 22 05:52:39 UTC 2024 - 23.6K bytes - Viewed (0)