Skip to content

Commit

Permalink
Add concrete changes for "Bug Fixes and Other Changes" field in relea…
Browse files Browse the repository at this point in the history
…se note.

PiperOrigin-RevId: 275942591
  • Loading branch information
shadowdragon89 authored and tensorflow-copybara committed Oct 21, 2019
1 parent 46e49bb commit 2cd974c
Showing 1 changed file with 45 additions and 1 deletion.
46 changes: 45 additions & 1 deletion RELEASE.md
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,51 @@ chaox
* After being deprecated for multiple years, as a part of tf.contrib deprecation, SessionBundle API will be removed starting from Tensorflow Serving 2.0 - if currently using SessionBundle, please migrate to SavedModel APIs.

## Bug Fixes and Other Changes
* This release is based on TF version 1.15.0
* Add monitoring config (commit: 18db9a46168eadd4d3e28e9b0cdb27bd6a11add9)
* Fix docs (commit: 7fc2253157db1dff340d7b418a6cf5204db2ce09)
* Use master as references (commit: 08cb506672d4c2ef289f79eee545df26d6577b45)
* Fix docs (commit: 9cc986beb742c485a62637fd20e841288774585d)
* Remove hyphen from version numbers to conform with PIP. (commit: 4aa0cfc24098000163fdfe270c4eb205e98790b1)
* Fix ImportError: No module named builtins (commit: e35ffff3999be3f971fa1503c158f33d721228c8)
* Cleanup visibility specs. (commit: 8e3956cac1eec2213538d8d6c367398e2f883e70)
* Remove 'future' from setup.py (commit: 64a80dd955a384de776b6256f3abcaa28cf88e79)
* Install future>=0.17.1 during Dockerfile.devel-gpu build (commit: dc36c21df5117364a3390a8bfe1fd3bf7dc92cb7)
* Replace calls to deprecated googletest APIs SetUpTestCase/TearDownTestCase with SetUpTestSuite/TearDownTestSuite. (commit: 39bbeb70dec8054d8ad81a7aa0423ec7e1a07c2a)
* Add the option to allow assigning labels to unavailable models in open source model server. (commit: e6d91e72f7593be36dda933b3291c7ebbc646fa6)
* Adds polling for config file to model server (#1301) (commit: c3eeed4f245e43f6cf92329d251e2b9d6255d6e5)
* Adds util functions for getting min of two ResourceAllocations. (commit: ba6527c8d56a0752f6c87115071e4d1bf7941810)
* Cleanup usage of the protobuf_archive. See #19032 (commit: dca61db5137c416a454c6ef821ad0fac6d66dc91)
* Replace NumSchedulableCPUs() with MaxParallelism(). (commit: aa9dddb93576c814b97947d6386d400cf6c87679)
* Don't run model_servers:tensorflow_model_server_test under asan (commit: b5c24e3e3849978a551db3aae3854c8794d10124)
* Release notes for 1.14 (commit: dc986268756ef45a3ffca4b8578dfdc69e015d29)
* Fixing Docker link (commit: 3bd851d88cd2febcdec29a52bab1d7d225a3a54c)
* Update release notes for 1.14.0 release. (commit: 00b2980a4d6ca127b63409b3eae791f846d1031a)
* Add release notes for TF serving 1.12.3. (commit: 7226859e9dd0f45bade559ab12892d4e388a7c11)
* Remove unnecessary calls to `Tensor::flat` in the tensorflow regressor interface. (commit: 55d897ef71b1ba142defec67bcce8eba7d8f5236)
* Fix print syntax in sample code (commit: ecef0d2fea2af1d4653a41934649512aa6994fd0)
* Adds guide for serving with custom ops (commit: dae0b4dffb29efc647783d45c28c4db0282b4d51)
* Return more informative error message during warmup. (commit: 1126fcd5d179d7829f48471eca6ddbbce79e219e)
* Enables passing in the SessionMetadata to the TensorFlow Session through the SavedModel ingestion API. (commit: 9cf3ff32daaaa2bb941ba7d7b8f049f807e4288e)
* Modifies server configuration documentation (commit: ee4edd59ad5ea088f1a6616cc6de531f66f25c3d)
* Fixes bazel build errors. (commit: bc07ec9015cba820be7f1087153d216964bd1a0b)
* Add tf.distribute + Keras model save/load test in TF serving. (commit: 093734d002bd9de2a68d34160e23f35db196c080)
* Remove unused fields from MetaGraphDef proto message, stored in (commit: 1f8f2902b6465f239bb58af2b3fb27ba73b5c7c5)
* Fix typo (missing colon) in comment. (commit: 561cabbabe9d44da6b20fcf0eb9170859d3ea9fe)
* Makes ServerCore::Log(...) mockable. (commit: 4b00a803faea0b96c9cbce6fbe23dfaec93bfbd4)
* Uses VerifyFunctionInternal to replace VerifyResourceValidityInternal and VerifyValidityInternal. (commit: b7b3c33422bb5cf0813fdd6604742e7fa3841f84)
* Removed the net_http dependency on absl/base/internal/raw_logging. (commit: 4e12a193ad27fa31cb1e42e9a7fe7b5c08f74c52)
* Override TF defined Abseil version to a more recent version, (commit: 1c0291118f34ec7ba958a9cee594414f6531c0f3)
* Makes VerifyValidity, Normalize and IsNormalized method virtual. (commit: 071634e39f47cde52996c8bfd1ddda8abf4deef9)
* Example of creating tf_serving_warmup_requests (commit: 1623705e4205bc779109f8c4d1eadf6d3f24a549)
* Don't copy SignatureDef. (commit: 28d32a1e487666c8b324c74afb633006ba5cbf17)
* Update resnet_warmup.py example (commit: 00b49bd3f4bcb3b17d1fb61bf302aacccf80c83e)
* Update resnet_warmup.py example (commit: 263025f091dd60d415dd22e9667c0f37f11209ff)
* Instrument BatchingSession::Run with TraceMe (commit: 929ab172ec3553a9d563b13dccfb0926d8bf3724)
* Remove contrib ops from model server from tensorflow 2.0. (commit: e7c987d4b10ac751081c62595fcd18be7481e67a)
* Use C++14 by default. (commit: 41873601c73bcb91e403f9ddd70a168ae117ddb0)
* o Switch to using the half_plus_two model from TF to tensorflow_serving one. (commit: 3ba8a6d8ac31572548bbe7922e4152a6b92e626c)
* Add TfLiteSession class to run inference on TensorFlow Lite Model. (commit: f2407e2011b5fc6d255c0ea54181f9cdd1d691e5)
* Add ability to load+run TF Lite model in ModelServer. (commit: d16ceafa044932e2d9ef84bbe1a6ae5c6356252f)

## Thanks to our Contributors

Expand Down

0 comments on commit 2cd974c

Please sign in to comment.