onnxruntime/onnxruntime/core
RandySheriffH d6849bd26c
Rashuai/cuda top k (#1919)
* implement cuda topk

* implement heap

* add type support

* refactor interface

* add support for sorting by index

* add test case

* use cub device radix sort

* register for opset 9 and 10

* add opset 9/10 delaration

* refactor code

* refactor code

* fix comment

* fix comment

* switch to scratched mem
2019-10-31 10:26:00 -07:00
..
automl/featurizers/src/FeaturizerPrep Commit formatting and end of lines (#2161) 2019-10-19 19:49:40 -07:00
codegen [NupharEP] performance improvements (#2283) 2019-10-30 10:15:04 -07:00
common Add missing guards to profiling calls (#1374) 2019-10-31 14:28:49 +10:00
framework Fixed tensor reference to const data and cleaned up Env API. (#1979) 2019-10-24 10:28:13 -07:00
graph Add node and op type info to error message if there's a type or shape inferencing exception thrown by the ONNX checker (#2277) 2019-10-29 23:42:13 -07:00
language_interop_ops Move CXX API global into the header (#2228) 2019-10-23 14:15:53 -07:00
mlas Introduce a separate check and conditional for AVX512BW build (#2083) 2019-10-10 16:14:00 -07:00
optimizer handle Concat-11 (#2240) 2019-10-23 19:12:40 -07:00
platform Fixed tensor reference to const data and cleaned up Env API. (#1979) 2019-10-24 10:28:13 -07:00
protobuf Bump up ONNX to the latest commit (#1868) 2019-09-20 18:15:16 -07:00
providers Rashuai/cuda top k (#1919) 2019-10-31 10:26:00 -07:00
session Relax check for optimized model saving (#2291) 2019-10-30 21:48:49 -07:00
util Update eigen to the latest version (#1910) 2019-10-11 10:44:19 -07:00