HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Docs Prettier reformat (#13483)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher 2024-06-10 12:59:01 +02:00 • committed by GitHub
parent 2f2e81614f
commit e5185ccf63
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
90 changed files with 763 additions and 742 deletions
Download patch file Download diff file Expand all files Collapse all files

10
docs/en/guides/optimizing-openvino-latency-vs-throughput-modes.md
View file

@ -36,12 +36,12 @@ Throughput optimization is crucial for scenarios serving numerous inference requ
1. **OpenVINO Performance Hints:** A high-level, future-proof method to enhance throughput across devices using performance hints.
```python
import openvino.properties.hint as hints
```python
import openvino.properties.hint as hints
config = {hints.performance_mode: hints.PerformanceMode.THROUGHPUT}
compiled_model = core.compile_model(model, "GPU", config)
```
config = {hints.performance_mode: hints.PerformanceMode.THROUGHPUT}
compiled_model = core.compile_model(model, "GPU", config)
```
2. **Explicit Batching and Streams:** A more granular approach involving explicit batching and the use of streams for advanced performance tuning.