ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Chronos: train tcn model on gpu and speed up inference on cpu (#5594)

Browse source 
* add nano_gpu

* simplify the code

* simplify the code

* modify the code

* add some updates

* add document

Co-authored-by: theaperdeng <theaperdeng@outlook.com>
This commit is contained in:
David smurf 2022-09-09 13:07:22 +08:00 committed by GitHub
parent dcff01690b
commit c73fc9f6ad
2 changed files with 14 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
docs/readthedocs/source/_static/js/chronos_tutorial.js
View file

@ -51,7 +51,8 @@ $(".checkboxes").click(function(){
var ids = ["ChronosForecaster","TuneaForecasting","AutoTSEstimator","AutoWIDE",
"MultvarWIDE","MultstepWIDE","LSTMForecaster","AutoProphet","AnomalyDetection",
"DeepARmodel","TFTmodel","hyperparameter","taxiDataset","distributedFashion",
"ONNX","Quantize","TCMFForecaster","PenalizeUnderestimation"];
"ONNX","Quantize","TCMFForecaster","PenalizeUnderestimation",
"GPUtrainingCPUacceleration"];
showTutorials(ids);
var disIds = ["simulation"];
disCheck(disIds);
@ -94,7 +95,7 @@ $(".checkboxes").click(function(){
disCheck(disIds);
}
else if(vals.includes("customized_model")){
var ids = ["AutoTSEstimator","DeepARmodel","TFTmodel"];
var ids = ["AutoTSEstimator","DeepARmodel","TFTmodel", "GPUtrainingCPUacceleration"];
showTutorials(ids);
var disIds = ["anomaly_detection","simulation","onnxruntime","quantization","distributed"];
disCheck(disIds);
@ -114,7 +115,7 @@ $(".checkboxes").click(function(){
disCheck(disIds);
}
else if(vals.includes("forecast") && vals.includes("customized_model")){
var ids = ["DeepARmodel","TFTmodel","AutoTSEstimator"];
var ids = ["DeepARmodel","TFTmodel","AutoTSEstimator","GPUtrainingCPUacceleration"];
showTutorials(ids);
var disIds = ["anomaly_detection","simulation","onnxruntime","quantization","distributed"];
disCheck(disIds);

10
docs/readthedocs/source/doc/Chronos/QuickStart/index.md
View file

@ -244,6 +244,16 @@
</details>
<hr>
<details id="GPUtrainingCPUacceleration">
<summary>
<a href="https://github.com/intel-analytics/BigDL/tree/main/python/chronos/example/inference-acceleration">Accelerate the inference speed of model trained on other platform</a>
<p>Tag: <button value="forecast">forecast</button>&nbsp;<button value="customized_model">customized model</button></p>
</summary>
<img src="../../../_images/GitHub-Mark-32px.png"><a href="https://github.com/intel-analytics/BigDL/tree/main/python/chronos/example/inference-acceleration">View source on GitHub</a>
<p>In this example, we show an example to train the model on GPU and accelerate the model by using onnxruntime on CPU.</p>
</details>
<hr>
</div>
<script src="../../../_static/js/chronos_tutorial.js"></script>