saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-18 21:21:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
2136 commits 2856 branches 57 tags 1.3 GiB
Commit graph

15 commits

Author SHA1 Message Date
Ashwini Khade
7c6242b024
update default optimization level + fix gemm_activation fusion (#2791) 
* update defualt optimization level + fix gemm_activation fusion

* fix typo

* add unit test and incorporate review comments

* fix test comment
 2020-01-13 14:05:38 -08:00
Changming Sun
013642ed37 Revert "Change default optimization level to All (from Basic) (#2745)" 
This reverts commit 56bb503c2f.
 2020-01-03 15:28:23 -08:00
Ashwini Khade
56bb503c2f
Change default optimization level to All (from Basic) (#2745) 
* change default optimization level to All (from Basic)

* fix test

* fix c# test
 2019-12-30 12:31:44 -08:00
Sreekanth Yalachigere
31ea11a696 Renaming MKL-DNN as DNNL (#2515) 
* DNNL: Moving Files to rename file names

* DNNL name change

* azure pipeline updated

* disable ceil/dialation and enable Opset10

* disable ceil/dialation tests in Python

* mlperf_ssd_resnet34_1200 disabled
 2019-12-03 07:34:23 -08:00
Nathan
0dd781fd57 Perf tuning doc update with latest API (#2128) 
* Update perf tuning md

* Remove AppendExecutionProvider
 2019-10-19 21:03:09 -07:00
Ashwini Khade
fc3c168402
Graph Optimizations Doc (#2050) 
* Initial draft

* updates per review

* fix link

* plus one more link fix

* small changes to the optimizer documentation

* some more changes

* done

* update C_API with doc link
 2019-10-18 08:03:40 -07:00
Faith Xu
ec136ac60f
Documentation Refresh (#1990) 
Various documentation updates, primarily for EP and main readme page
 2019-10-15 15:58:02 -07:00
Pranav Sharma
91db840b6b
Introduce execution mode enum for clarity and extensibility; Change Python, C and C# APIs accordingly; Removed EnableSequentialExecution, DisableSequentialExecution in favor of the more general SetExecutionModeAPI. (#2098) 
* Introduce execution mode for clarity and extensibility; Change Python APIs accordingly; Replace DisableSequentialExecution API with EnableParallelExecution for clarity.

* Fix cuda build

* Modify the test slightly

* Make C and C# APIs consistent with Python.
 2019-10-14 09:48:19 -07:00
Emma Ning
02c122d6e4 Add OLive in perf tuning section (#1772) 
* Add OLive in perf tuning section

* Add OLive to perf tuning section

* Update README.md

* Update ONNX_Runtime_Perf_Tuning.md
 2019-09-27 13:10:40 -07:00
Pranav Sharma
a9ce941579
Refine threading control options and move inter op thread pool to session state. (#1841) 
Description: Refine threading control options and move inter op thread pool to session state.
Added thread_utils.h/cc to centralize the decision around the thread pool size under various conditions.

Motivation and Context
Currently the thread pool size of the parallel executor is hardcoded to 32 for some reason. This PR makes the options to configure the thread pool sizes clearer.
 2019-09-18 22:36:23 -07:00
Pranav Sharma
377dcf60ac
Update onnx test runner documentation (#1651) 
* Mention OrtCreateSessionFromArray in C API doc

* Update perf tool documentation to reflect the new graph optimization enums. Relax constraint for enable_all.

* Update one more doc

* Update onnx test runner documentation

* Add default in the docs
 2019-08-19 18:28:09 -07:00
Pranav Sharma
6f3a835d38 Update perf tool documentation to reflect the new graph optimization enums. Relax constraint for enable_all. (#1650) 2019-08-19 14:27:33 -07:00
Chris Seymour
db61eb4cd7 Update ONNX_Runtime_Perf_Tuning.md (#1378) 2019-07-17 19:14:43 -07:00
ybrnathan
a79ab5ec5b
Add document for ONNX Runtime latency profiling and JSON file viewing. (#1301) 2019-06-26 21:58:10 -07:00
ybrnathan
18b7d2b18a
Add document of ONNXRuntime performance tuning (#1266) 
* Add document of ONNXRuntime performance tuning

* Clarify MKL-ML
 2019-06-21 10:38:22 -07:00