Chin Huang
Chin Huang
/kind feature **Describe the solution you'd like** Currently, the model type + version support for Serving Runtimes (SR) is not limited to a specific version. For example, a SR with...
Hello, everyone! I would like to know who is using onnx-tensorflow converter. If you are one of them, please leave a comment. We are currently short of development resources and...
**What this PR does / why we need it**: Currently explainers don't work when the inference service deploymentMode is ModelMesh. This PR enables KServe explainers to work with ModelMesh. **Which...
/kind feature **Describe the solution you'd like** I would like the existing KServe explainers to work with Modelmesh. **Anything else you would like to add:** The explainers currently work with...
ONNX allows a tensor-type to have no shape (which means that even the rank is unknown). A tensor type may have a shape, in which case its rank is known....
We would like to evaluate the feasibility of the ONNX training proposal, https://github.com/onnx/onnx/issues/2038, and share our results with the Training WG and converter SIG. The goal of this issue/task is...
The system configuration or backend framework versions between the conversion and execution servers can be different in practice. One might use a CPU machine to convert the model and a...
Currently there is no unit test for onnx-ml operators. We would like to identify how converters can verify and claim support of onnx-ml operators. Also figure out how to report...