saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-19 19:00:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

olive doc update (#15261)

Browse source 
Olive v2 has been released, and we need to update the doc related to
Olive v1.
This commit is contained in:
leqiao-1 2023-03-30 03:49:06 +08:00 committed by GitHub
parent b2393480ee
commit 8f04e2bea5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
docs/performance/tune-performance/profiling-tools.md
View file

@ -14,11 +14,11 @@ nav_order: 1
{:toc}
## ONNX Go Live Tool (OLive)
## Olive
The [ONNX Go Live "OLive" tool](https://github.com/microsoft/OLive) is a Python package that automates the process of accelerating models with ONNX Runtime. It contains two parts: (1) model conversion to ONNX with correctness validation (2) auto performance tuning with ORT. Users can run these two together through a single pipeline or run them independently as needed.
[Olive](https://github.com/microsoft/Olive) is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation. Given a model and targeted hardware, Olive composes the best suitable optimization techniques to output the most efficient model(s) for inferencing on cloud or edge, while taking a set of constraints such as accuracy and latency into consideration.
As a quickstart, please see the [notebook tutorials](https://github.com/microsoft/OLive/tree/master/notebook-tutorial) and [command line examples](https://github.com/microsoft/OLive/tree/master/cmd-example)
As a quickstart, please refer to [documentation](https://microsoft.github.io/Olive) and [examples](https://github.com/microsoft/Olive/tree/main/examples).
## In-code performance profiling