HomePhabricator

Add CalibratedQuantizedType to quant dialect

Authored by Tei Jeong <taeheej@google.com> on Nov 17 2020, 10:14 PM.

Description

Add CalibratedQuantizedType to quant dialect

This type supports a calibrated type with min, max provided.

This will be used for importing calibration values of intermediate tensors (e.g. LSTM) which can't be imported with QuantStats op.

This type was initially suggested in the following RFC: https://llvm.discourse.group/t/rfc-a-proposal-for-implementing-quantization-transformations-in-mlir/655

Reviewed By: stellaraccident

Differential Revision: https://reviews.llvm.org/D91584

Details

Committed
liufengdbNov 17 2020, 10:14 PM
Reviewer
stellaraccident
Differential Revision
D91584: Add CalibratedQuantizedType to quant dialect
Parents
rG4bc085f5b3ed: [clangd] Add OverridenBy Relation to index.
Branches
Unknown
Tags
Unknown