- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for PrepareDynamicRangeQuantizableOp (0.19 sec)
-
tensorflow/compiler/mlir/lite/transforms/prepare_quantize_dynamic_range.cc
// If the weight is applicable to dynamic range quantization, insert Quantize // and Dequantize ops with either per-axis or per-tensor scale. class PrepareDynamicRangeQuantizableOp : public OpRewritePattern<arith::ConstantOp> { public: explicit PrepareDynamicRangeQuantizableOp( MLIRContext* context, const quant::QuantizationSpecs& quant_specs, llvm::SetVector<Operation*>* const visited_nonquantizable_ops)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 20.8K bytes - Viewed (0)