Commit graph

29 commits

Author SHA1 Message Date
Hariharan Seshadri
cfb08c4848
TopK op: Promote onnx to a newer commit and handle changed TopK spec for opset 10 (#611)
* Initial commit

* Nit fix
2019-03-13 10:21:58 -07:00
Ke Zhang
5bb842538d
sync onnx and maintain old version history for removed exp ops (#588)
* sync onnx and maintain old version history for removed exp ops in onnx runtime.

* update

* updating to specific onnx commit - remove exp ops.

* update

* disable the 3 failures to push the change as it's blocking folks.

* update test
2019-03-12 18:48:27 -07:00
Hariharan Seshadri
1d3fcc525a
deps: update onnx to a newer commit and update test exclusions (#542)
* Update onnx dep to a newer commit and update test exclusions

* Keeping shrink excuded in c++ tests

* More changes
2019-03-05 12:03:16 -08:00
Dmitri Smirnov
0e687a2c90
Implement tokenex regular expression matching and add tests. (#480)
* Implement tokenex regular expression matching and add tests.
  Import re2 module.
2019-02-20 15:56:32 -08:00
Raymond Yang
ec8ac04f30
Update cast op to support string <-> numeric (#379)
* Update cast kernel to support to/from string

* Update namespace

* Add support for literal numeric case

* Update to support -INF test

* Update kernel registration for cast

* Update ONNX to 1.4.1

* Update registy api

* Resolve some comments

* Update cast kernel implementation

* Resolve comments

* Fixed test data in onnx

* Update cast kernel implementation

* Resolve PR comments

* Update cast_op.cc

* Update onnx commits info

* Update comments
2019-02-12 10:10:56 -08:00
Scott McKay
bca8daf762
Update ONNX. Implement Scan 9 changes (#366)
* Update ONNX version to pickup Scan spec change that adds scan_output_axes.
Add logic to transpose an output
  - write to temporary buffer when executing subgraph
  - transpose temporary buffer into Scan output when execution completes
Add unit tests

* Update to ONNX dbf3581835e3a05716e10587511d7ab3b2cdc386 to pickup inferencing bugfix.
Update test to match.

* Disable some tests for opset 9 operators that haven't been implemented yet.
2019-01-24 08:10:39 +10:00
stevenlix
8ea7197b82 trt (#361)
* updated cmake files for tensorrt
2019-01-23 13:28:13 -08:00
Changming Sun
948cc03490 upgrade onnx 2019-01-17 13:10:30 -08:00
Changming Sun
8cfe8d33a3 Add nsync (#292)
* Add nsync

* nsync2

* nsync3

* fix build

* update comments

* fix build option
2019-01-09 10:40:55 -08:00
Pranav Sharma
31bbb4598e
Enable tvm in CI builds. (#285)
* Enable tvm in CI builds

* Fix tvm dll path issue
2019-01-07 19:37:06 -08:00
Ke Zhang
386b60e35a
update gemmlowp which carries a windows build break fix. (#291) 2019-01-07 18:24:46 -08:00
Yang Chen
4929ddde43 update tvm submodule (#287) 2019-01-07 14:32:58 -08:00
Changming Sun
5e113661a9 Build system upgrades (#281)
* update

* runas normal user
2019-01-07 13:15:24 -08:00
xkszltl
bddeb3d001 Fix "invalid escape" issue when eigen_SOURCE_PATH contains "\". (#258) 2019-01-02 14:00:21 -08:00
Dmitri Smirnov
7af1887b33
Introduce basic BFloat16 runtime support (#235)
* Add basic support for BFloat16 type.

* Advance onnx submodule for bfloat16 support.

* Update install_deps for linux.

* Address review comments.
2018-12-21 12:40:59 -08:00
jywu-msft
eb867be331
update mkldnn to 0.17.2 (#231) 2018-12-20 07:32:49 -08:00
Changming Sun
e97caa7787 change mkldnn so path (#210) 2018-12-19 14:45:57 -08:00
Changming Sun
dc8b37f4c4
update onnx (#209)
* update onnx
2018-12-18 14:50:28 -08:00
Ke Zhang
37b74c771a
add gemmlowp as submodule. (#206) 2018-12-18 13:57:53 -08:00
Changming Sun
c0ec7d56c4
Clean up garbage files (#208) 2018-12-18 13:51:01 -08:00
KeDengMS
b0f27ba0a7
Allow using MKLML header/libs when use_mklml is specified (#178)
Allow using MKLML header/libs when use_mklml is specified
2018-12-17 14:41:42 -08:00
xkszltl
383315a7e0 Upgrade Eigen to 3.3.7 (#185) 2018-12-16 00:26:08 -08:00
Ashwini Khade
c5a691d67d
update onnx to latest commit (#132)
* update onnx to latest commit

* fixes

* Add not implemented operator tests to whitelist

* fix test name
2018-12-10 11:17:52 -08:00
jywu-msft
47a6992e1b
update mkldnn to 0.17.1 and address assumptions related to tensor padding that come with new mkldnn version. (#79) 2018-12-03 17:07:44 -08:00
George Wu
3feeb9de3e Merge branch 'master' of https://github.com/Microsoft/onnxruntime into jywu/incr_fixup 2018-11-28 20:16:06 -08:00
Yulong Wang
846044e282 [Mac] support mkldnn for macOS (#56) 2018-11-28 20:01:21 -08:00
George Wu
6179ddb2a1 fix for possible incremental build breaks. 2018-11-28 18:14:20 -08:00
Pranav Sharma
9fbcb7fa51 Update onnx to commit to pickup shape inference fix for broadcast, concat and scan 2018-11-20 19:41:30 -08:00
Pranav Sharma
89618e8f1e Initial bootstrap commit. 2018-11-19 16:48:22 -08:00