Commit message (Expand) | Author | Age | |
---|---|---|---|
* | Fix include guards | A. Unique TensorFlower | 2018-08-16 |
* | Add GPU support for float16 batched matmul (#18436) | Ben Barsdell | 2018-05-10 |
* | Use tensorflow::se instead of perftools::gputools for StreamExecutor. | Justin Lebar | 2018-04-23 |
* | Cleanup: Ran clang-format on all *.{cc,h} files in tensorflow/core/kernels. | A. Unique TensorFlower | 2018-01-26 |
* | Disable parallelizing over both batch and inner matrix dimensions in CPU Batc... | A. Unique TensorFlower | 2017-10-03 |
* | Merge changes from github. | Jonathan Hseu | 2017-06-09 |
* | Improves performance of tf.matmul(a, b, ...) for dense tensors on NVIDIA GPUs... | A. Unique TensorFlower | 2017-03-17 |
* | Shard batch_matmul_op across files to speed up build. | A. Unique TensorFlower | 2016-09-30 |