Thijsvandepoll

Extremely slow inference speed

15

### 🐛 Describe the bug I am trying to deploy a PyTorch model retrieved from Huggingface (SentenceBert-like model) inside TorchServe in Docker. I have done the following: 1. Create a...

This will solve issue #307, which caused inconsistent preprocessing steps. This resulted in the possibility that a self-comparison could result in another score than 100. For example, ``` list(process.extractWithoutOrder("杰弗里·S·布里特", ["杰弗里·S·布里特"],...

Hi all, I found a bug in `process.extractWithoutOrder()` which causes `process.dedupe()` to fail unexpectedly. The example: ``` process.dedupe(["BRITT JEFFREY S", "BRITT JEFFREY S.", "WIEDEMAN SCOTT", "WIEDERMANN SCOTT", "斯科特·维德曼", "杰弗里·S·布里特"]) ```...

How to load model from .tar.gz/.tgz?

4

Hi all, I am new to KServe and Modelmesh Serving and try to get to know the software. I am trying to combine Kubeflow with Modelmesh Serving by using the...