Junwei Deng

Chronos: Move `orca.automl.metrics` to `Chronos`

1

- Since `orca.automl` is used for customized model for any area, while most of the metrics in `orca.automl.metrics` is designed and optimized for time series tasks. - The built-in metrics...

We need a user guide for developer in our wiki/external doc

Ray >= 1.0.0 has enable the implicitly search space transformation for a majority of search space except SigOpt.

Chronos TSDataset: various enhancement

7

- [x] Enable customized feature generation in `gen_dt_feature`. - [x] API doc for TSDataset. - [ ] Onehotencoder operation. - [x] _unscale_numpy -> unscale_numpy with api doc - [x] resample...

#### Background Evaluation has become an important topic in our engagement with customers. There are many aspects we need to enhance our evaluator. - Acurracy - Quantitative: Currently we have...

Nano: Model optimization pipeline APIs

1

## Background Nano currently has a great collection of pytorch/tf inference acceleration methods, while our users might need an automatical (intellectural guided) pipeline to find which one is the best....

## Description ### 1. Why the change? Refactor the how-to guides structure, add a new alg choice page. ### 3. Summary of the change A new how-to guide index page:...

## Description ### 1. Why the change? related to #5335 ### 2. User API changes related to #5335 ### 3. Summary of the change related to #5335 ### 4. sample...

Nano: add ipex and jit options to `bigdl.nano.pytorch.Trainer.trace`

2

## Motivation Since we find for some models(e.g. Autoformer in Chronos), JIT and ipex brings some improvement on inference latency while Onnxruntime and OpenVINO can not work properly (e.g. lack...

## motivation This is inspired by https://docs.openvino.ai/latest/openvino_inference_engine_tools_benchmark_tool_README.html. We need a benchmark tool for developers and users to benchmark the training and inferencing performance on their own platform. Our users need...