aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/core/kernels/partitioned_function_ops.cc
Commit message (Expand)AuthorAge
* Error out when PartitionedCall is created with the wrong number of arguments.Gravatar Alexandre Passos2018-10-04
* Adding check around AddFunctionLibraryGravatar Niranjan Hasabnis2018-09-25
* Fix for failing eager:function_testGravatar Niranjan Hasabnis2018-09-20
* Addressing review comments: indentationGravatar Niranjan Hasabnis2018-09-17
* [Intel MKL] Fixes for unit test failuresGravatar Niranjan Hasabnis2018-09-14
* Change HandleFromInput() to return a `const ResourceHandle&` and avoid copyin...Gravatar Derek Murray2018-09-12
* Construct placer after the first optimization pass is run.Gravatar Akshay Modi2018-09-11
* Run graph optimization passes in PartitionedCallOp.Gravatar Akshay Agrawal2018-09-07
* Add the device (stack) to tfe.defun's cache key, and copy the device stackGravatar Akshay Agrawal2018-08-22
* Fix incorrect early-out in partitioning.Gravatar Akshay Agrawal2018-08-10
* Propagate local device to nodes without device annotations in PartitionedCallOp.Gravatar Akshay Agrawal2018-08-10
* Fix use-after-free in (Stateful)PartitionedCallOp.Gravatar Akshay Agrawal2018-08-08
* Allow differentiating tfe.defun functions which contain conds.Gravatar Alexandre Passos2018-07-23
* Exempt partitioned function calls from the Placer's constraint on resourceGravatar Akshay Agrawal2018-07-07
* Make functions defined with tfe.defun respect devices when executing.Gravatar Akshay Agrawal2018-07-03
* Minor touch ups to PartitionedCallOp.Gravatar Akshay Agrawal2018-06-06
* `PartitionedCallOp`: An op for executing multi-device functions.Gravatar Akshay Agrawal2018-04-24
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-15 16:02:57 +0000