Trawinski, Dariusz

@tanmayv25 Related change in the openvino_backend is included in https://github.com/triton-inference-server/openvino_backend/pull/74/files Merge is pending your review for this PR. If you are ok with this approach, the first step would be...

> We should add some testing in our CI for the support target_device. Something like this: https://github.com/triton-inference-server/server/blob/main/qa/L0_libtorch_inference_mode/test.sh > > We can call it L0_openvino_target_device? Functional tests are under preparation in...

on main branch we could switch now to 2024.2 version from ov master

This PR is a replacement for https://github.com/huggingface/optimum-intel/pull/519

@slyalin @eaidova can you add your comments?

@Xaenalt my observation is that without the entitlement and subscription it is not possible to install via yum the package cuda-11-8: `requires cuda-runtime-11-8 >= 11.8.0, but none of the providers...

@Xaenalt here are my steps to reproduce: on branch https://github.com/openvinotoolkit/model_server/tree/cuda-ubi-1 I'm building on ubuntu20 host with a command: make docker_build BASE_OS=redhat NVIDIA=1 OV_USE_BINARY=0 It fails on step `yum install -y...

The changes are incorporated in the main branch. Thank you for your contribution.

@hilliao We are going to drop this demo and replace it with a gRPC streaming client with graph example based on MediaPipe graphs. https://github.com/openvinotoolkit/model_server/pull/2170 This new functionality improved the communication...

currently we don't have plans for adding the image for Raspberry Pi in docker_ci tools. This should be however doable while OpenVINO does support ARM architecture. https://github.com/openvinotoolkit/openvino_contrib/tree/master/modules/arm_plugin You can read...