Hello, I am interested in using v1.20.0 on openvino hardware as the new version claims to have optimized first inference latency. It seems that v1.20.0 has been released for onnxruntime-gpu but not onnxruntime-openvino yet.
Also is there any more information on how much the first inference latency has been improved?
Describe the issue
Hello, I am interested in using v1.20.0 on openvino hardware as the new version claims to have optimized first inference latency. It seems that v1.20.0 has been released for onnxruntime-gpu but not onnxruntime-openvino yet.
Also is there any more information on how much the first inference latency has been improved?
Thanks!
To reproduce
N/A
Urgency
No response
Platform
Linux
OS Version
N/A
ONNX Runtime Installation
Released Package
ONNX Runtime Version or Commit ID
N/A
ONNX Runtime API
Python
Architecture
X64
Execution Provider
OpenVINO
Execution Provider Library Version
No response