You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* Update README.md (#3472)
Co-authored-by: ishaghosh27 <[email protected]>
* added import os for exit() to fix NameError (#3475)
Name error coming up on code if reached to that line,
Co-authored-by: Harish Vadaparty <[email protected]>
* [Doc] Update Custom OPs broken references (#739)
Signed-off-by: Emmanuel Ferdman <[email protected]>
Small PR - Commit f63ed97 moved a bunch of files. This PR adjusts the source for changes.
* Add options to build with system LIBXSMM/oneDNN/sleef/MKL/ideep/gtest
Signed-off-by: Sv. Lockal <[email protected]>
---------
Signed-off-by: Sv. Lockal <[email protected]>
Co-authored-by: ishaghosh27 <[email protected]>
Co-authored-by: Harish Vadaparty <[email protected]>
Co-authored-by: Emmanuel Ferdman <[email protected]>
Co-authored-by: Sv. Lockal <[email protected]>
Copy file name to clipboardExpand all lines: examples/cpu/inference/python/jupyter-notebooks/README.md
+6-4Lines changed: 6 additions & 4 deletions
Original file line number
Diff line number
Diff line change
@@ -2,15 +2,17 @@
2
2
3
3
Intel® Extension for PyTorch (IPEX) extends PyTorch* with optimizations for extra performance boost on Intel® hardware. While most of the optimizations will be upstreamed in future PyTorch* releases, the extension delivers up-to-date features and optimizations for PyTorch workloads on Intel® hardware. The optimization approaches generally include operator optimization, graph optimization and runtime optimization.
4
4
5
+
Before selecting a sample, please make sure to (1) Check [Prerequisites](#prerequisites), (2) complete [Environment Setup](#environment-setup), and (3) see instructions to [Run the Sample](#run-the-sample).
6
+
5
7
## Jupyter Notebooks Overview
6
8
7
9
| Sample name | Description | Time to Complete | Category | Validated for AI Tools Selector |
8
10
|---|---|---|---|---|
9
11
[Getting Started with Intel® Extension for PyTorch* (IPEX)](https://github.com/intel/intel-extension-for-pytorch/tree/main/examples/cpu/inference/python/jupyter-notebooks/IPEX_Getting_Started.ipynb) | This code sample demonstrates how to begin using the Intel® Extension for PyTorch* (IPEX). It will guide users how to run a PyTorch inference workload on CPU by using oneAPI AI Analytics Toolkit and also analyze the CPU usage via oneDNN verbose logs.| 15 minutes| Getting Started | Y |
10
-
[PyTorch Inference Optimizations with Intel® Advanced Matrix Extensions (Intel® AMX) Bfloat16 Integer8](https://github.com/intel-innersource/frameworks.ai.pytorch.ipex-cpu/blob/cpu-device/examples/cpu/inference/python/jupyter-notebooks/IntelPyTorch_InferenceOptimizations_AMX_BF16_INT8.ipynb) | This code sample demonstrates how to perform inference using the ResNet50 and BERT models using the Intel® Extension for PyTorch* (IPEX). IPEX allows you to speed up inference on Intel® Xeon Scalable processors with lower precision data formats and specialized computer instructions. The bfloat16 (BF16) data format uses half the bit width of floating-point-32 (FP32), which lessens the amount of memory needed and execution time to process. Likewise, the integer8 (INT8) data format uses half the bit width of BF16. | 5 minutes | Code Optimization | Y|
11
-
[Interactive Chat Based on DialoGPT Model Using Intel® Extension for PyTorch* Quantization](https://github.com/intel-innersource/frameworks.ai.pytorch.ipex-cpu/blob/cpu-device/examples/cpu/inference/python/jupyter-notebooks/IntelPytorch_Interactive_Chat_Quantization.ipynb)| This code sample demonstrates how to create interactive chat based on pre-trained DialoGPT model and add the Intel® Extension for PyTorch* (IPEX) quantization to it. The sample shows how to create interactive chat based on the pre-trained DialoGPT model from HuggingFace and how to add INT8 dynamic quantization to it. The Intel® Extension for PyTorch* (IPEX) gives users the ability to speed up operations on processors with INT8 data format and specialized computer instructions.| 10 minutes | Concepts and Functionality| Y|
12
-
[Optimize PyTorch Models using Intel® Extension for PyTorch* (IPEX) Quantization](https://github.com/intel-innersource/frameworks.ai.pytorch.ipex-cpu/blob/cpu-device/examples/cpu/inference/python/jupyter-notebooks/IntelPytorch_Quantization.ipynb)|This code sample demonstrates how to quantize a ResNet50 model that is calibrated by the CIFAR10 dataset using the Intel® Extension for PyTorch* (IPEX). IPEX gives users the ability to speed up inference on Intel® Xeon Scalable processors with INT8 data format and specialized computer instructions. The INT8 data format uses quarter the bit width of floating-point-32 (FP32), lowering the amount of memory needed and execution time to process.| 5 minutes| Concepts and Functionality| Y|
13
-
[Optimize PyTorch Models using Intel® Extension for PyTorch* (IPEX)](https://github.com/intel-innersource/frameworks.ai.pytorch.ipex-cpu/blob/cpu-device/examples/cpu/inference/python/jupyter-notebooks/optimize_pytorch_models_with_ipex.ipynb)| This sample notebook shows how to get started with Intel® Extension for PyTorch* (IPEX) for sample Computer Vision and NLP workloads. The sample starts by loading two models from the PyTorch hub: Faster-RCNN (Faster R-CNN) and distilbert (DistilBERT). After loading the models, the sample applies sequential optimizations from Intel® Extension for PyTorch* (IPEX) and examines performance gains for each incremental change.| 30 minutes | Code Optimization |Y|
12
+
[PyTorch Inference Optimizations with Intel® Advanced Matrix Extensions (Intel® AMX) Bfloat16 Integer8](https://github.com/intel/intel-extension-for-pytorch/blob/main/examples/cpu/inference/python/jupyter-notebooks/IntelPyTorch_InferenceOptimizations_AMX_BF16_INT8.ipynb) | This code sample demonstrates how to perform inference using the ResNet50 and BERT models using the Intel® Extension for PyTorch* (IPEX). IPEX allows you to speed up inference on Intel® Xeon Scalable processors with lower precision data formats and specialized computer instructions. The bfloat16 (BF16) data format uses half the bit width of floating-point-32 (FP32), which lessens the amount of memory needed and execution time to process. Likewise, the integer8 (INT8) data format uses half the bit width of BF16. | 5 minutes | Code Optimization | Y|
13
+
[Interactive Chat Based on DialoGPT Model Using Intel® Extension for PyTorch* Quantization](https://github.com/intel/intel-extension-for-pytorch/blob/main/examples/cpu/inference/python/jupyter-notebooks/IntelPytorch_Interactive_Chat_Quantization.ipynb)| This code sample demonstrates how to create interactive chat based on pre-trained DialoGPT model and add the Intel® Extension for PyTorch* (IPEX) quantization to it. The sample shows how to create interactive chat based on the pre-trained DialoGPT model from HuggingFace and how to add INT8 dynamic quantization to it. The Intel® Extension for PyTorch* (IPEX) gives users the ability to speed up operations on processors with INT8 data format and specialized computer instructions.| 10 minutes | Concepts and Functionality| Y|
14
+
[Optimize PyTorch Models using Intel® Extension for PyTorch (IPEX) Quantization](https://github.com/intel/intel-extension-for-pytorch/blob/main/examples/cpu/inference/python/jupyter-notebooks/IntelPytorch_Quantization.ipynb)|This code sample demonstrates how to quantize a ResNet50 model that is calibrated by the CIFAR10 dataset using the Intel® Extension for PyTorch* (IPEX). IPEX gives users the ability to speed up inference on Intel® Xeon Scalable processors with INT8 data format and specialized computer instructions. The INT8 data format uses quarter the bit width of floating-point-32 (FP32), lowering the amount of memory needed and execution time to process.| 5 minutes| Concepts and Functionality| Y|
15
+
[Optimize PyTorch Models using Intel® Extension for PyTorch* (IPEX)](https://github.com/intel/intel-extension-for-pytorch/blob/main/examples/cpu/inference/python/jupyter-notebooks/optimize_pytorch_models_with_ipex.ipynb)| This sample notebook shows how to get started with Intel® Extension for PyTorch* (IPEX) for sample Computer Vision and NLP workloads. The sample starts by loading two models from the PyTorch hub: Faster-RCNN (Faster R-CNN) and distilbert (DistilBERT). After loading the models, the sample applies sequential optimizations from Intel® Extension for PyTorch* (IPEX) and examines performance gains for each incremental change.| 30 minutes | Code Optimization |Y|
14
16
15
17
>**Note**: For Key Implementation Details, please refer to the .ipynb file of a sample.
Copy file name to clipboardExpand all lines: tests/cpu/bench/custom_op_bench/README.md
+4-4Lines changed: 4 additions & 4 deletions
Original file line number
Diff line number
Diff line change
@@ -1,14 +1,14 @@
1
1
# Running benchmarks for Intel Extension for PyTorch Custom OPs
2
-
Evaluate performance for custom operator with [launcher](../../../../tutorials/intro_launch.md).
2
+
Evaluate performance for custom operator with [launcher](../../../../docs/tutorials/performance_tuning/launch_script.md).
3
3
## Prepare envrioment
4
-
Follow [performance_tuning_guide](../../../../tutorials/Performance_Tuning.md) to install Memory_Allocator(you can choose Tcmalloc or Jemalloc).
4
+
Follow [performance_tuning_guide](../../../../docs/tutorials/performance_tuning/tuning_guide.md) to install Memory_Allocator(you can choose Tcmalloc or Jemalloc).
0 commit comments