CristianJDiaz

I have a fine tuning TrOCR model, and i'm using `from optimum.onnxruntime import ORTModelForVision2Seq` how i can then make the inferation faster, when some one make a request in a...

Is there another way to quantized TrOCR model to speed the inference, i alreayd have in ONNX form but the inference time is to high

Speed inference Time

6

I'm using yolonas to detect handwrite numbers, and the inference time goes well locally, but when i deploy it in redhat openshift the inferece time increase, i had try to...

i had figured out how to create the same with anthropic LLM, the amazon titan support have support for that ?

I have data of covid-19, and this model in the paper said that is SOTA for times series, but against LSTM model relative small the performance is too low, i...

### 💡 Your Question Is it possible to use AWS Sagemaker inference endpoint , to deploy a yolo-nas object detection?, i'm kind of new in aws cloud, i search for...