Commit message (Expand) | Author | Age | |
---|---|---|---|
* | [XLA:TPU] Initial HLO parser/stringifier support for sparse formats | A. Unique TensorFlower | 2018-01-12 |
* | [XLA] Initial sparse layout support | A. Unique TensorFlower | 2018-01-08 |
* | [XLA] Fix return type of LayoutUtil::PaddedDimensions | A. Unique TensorFlower | 2017-12-19 |
* | [XLA] Add format field to layout | A. Unique TensorFlower | 2017-12-18 |
* | The new array class provides a way to simplify the implementation of | A. Unique TensorFlower | 2017-10-20 |
* | Lower vector-matrix dot to LLVM IR if the RHS of the dot can be made | Sanjoy Das | 2017-09-14 |
* | [TF:XLA] Fixes to the "evaluator" plugin. | Peter Hawkins | 2017-08-05 |
* | [XLA] Remove the xla_default_layout flag. | Eli Bendersky | 2017-07-21 |
* | Improve support for pad instructions with negative padding. | Mark Heffernan | 2017-01-23 |
* | [XLA] Recognize any reduction where dimensions to keep are consecutive in mem... | A. Unique TensorFlower | 2017-01-12 |
* | Initial open-source release of XLA: Accelerated Linear Algebra. | Peter Hawkins | 2017-01-09 |