Merge branch 'clean_1x' of https://github.com/intel/neural-compressor into clean_1x

Author: yiliu30

.azure-pipelines/scripts/models/run_pytorch_models_trigger.sh

@@ -53,15 +53,15 @@ elif [ "${model}" == "resnet18_fx" ]; then
     tuning_cmd="bash run_quant.sh --topology=resnet18 --dataset_location=${dataset_location} --input_model=${input_model}"
     benchmark_cmd="bash run_benchmark.sh --topology=resnet18 --dataset_location=${dataset_location} --mode=performance --batch_size=${batch_size} --iters=500"
 elif [ "${model}" == "opt_125m_woq_gptq_int4" ]; then
-    model_src_dir="nlp/huggingface_models/language-modeling/quantization/llm"
+    model_src_dir="nlp/huggingface_models/language-modeling/quantization/weight_only"
     inc_new_api=3x_pt
     tuning_cmd="bash run_quant.sh --topology=opt_125m_woq_gptq_int4"
 elif [ "${model}" == "opt_125m_woq_gptq_int4_dq_bnb" ]; then
-    model_src_dir="nlp/huggingface_models/language-modeling/quantization/llm"
+    model_src_dir="nlp/huggingface_models/language-modeling/quantization/weight_only"
     inc_new_api=3x_pt
     tuning_cmd="bash run_quant.sh --topology=opt_125m_woq_gptq_int4_dq_bnb"
 elif [ "${model}" == "opt_125m_woq_gptq_int4_dq_ggml" ]; then
-    model_src_dir="nlp/huggingface_models/language-modeling/quantization/llm"
+    model_src_dir="nlp/huggingface_models/language-modeling/quantization/weight_only"
     inc_new_api=3x_pt
     tuning_cmd="bash run_quant.sh --topology=opt_125m_woq_gptq_int4_dq_ggml"
 fi

README.md

@@ -5,7 +5,7 @@ Intel® Neural Compressor
 <h3> An open-source Python library supporting popular model compression techniques on all mainstream deep learning frameworks (TensorFlow, PyTorch, ONNX Runtime, and MXNet)</h3>
 
 [![python](https://img.shields.io/badge/python-3.8%2B-blue)](https://github.com/intel/neural-compressor)
-[![version](https://img.shields.io/badge/release-2.5-green)](https://github.com/intel/neural-compressor/releases)
+[![version](https://img.shields.io/badge/release-2.6-green)](https://github.com/intel/neural-compressor/releases)
 [![license](https://img.shields.io/badge/license-Apache%202-blue)](https://github.com/intel/neural-compressor/blob/master/LICENSE)
 [![coverage](https://img.shields.io/badge/coverage-85%25-green)](https://github.com/intel/neural-compressor)
 [![Downloads](https://static.pepy.tech/personalized-badge/neural-compressor?period=total&units=international_system&left_color=grey&right_color=green&left_text=downloads)](https://pepy.tech/project/neural-compressor)

conda_meta/basic/meta.yaml

@@ -95,7 +95,7 @@ user_model = convert(model=user_model)
 
 ## Examples
 
-- PyTorch [huggingface models](/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/mx)
+- PyTorch [huggingface models](/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/mx_quant)
 
 
 ## Reference

conda_meta/neural_insights/meta.yaml

@@ -46,7 +46,7 @@ run_fn(prepared_model)
 q_model = convert(prepared_model)
 ```
 
-To get more information, please refer to [examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/llm).
+To get more information, please refer to [examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/smooth_quant).
 
 
 ## Validated Models

conda_meta/neural_solution/meta.yaml

@@ -1,6 +1,5 @@
 PyTorch Static Quantization
 ========================================
-
 1. [Introduction](#introduction)
 2. [Get Started](#get-started) \
     2.1 [Static Quantization with IPEX Backend](#static-quantization-with-ipex-backend) \
@@ -9,6 +8,7 @@ PyTorch Static Quantization
         2.1.3 [Model Examples](#model-examples) \
     2.2 [Static Quantization with PT2E Backend](#static-quantization-with-pt2e-backend) \
         2.2.1 [Usage Sample with PT2E](#usage-sample-with-pt2e)
+        2.2.2 [Model Examples with PT2E](#model-examples-with-pt2e)
 
 
 ## Introduction
@@ -68,7 +68,7 @@ q_model = convert(prepared_model)
 
 #### Model Examples
 
-Users could refer to [examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/llm) on how to quantize a new model.
+Users could refer to [examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/static_quant/ipex) on how to quantize a new model.
 
 
 ### Static Quantization with PT2E Backend
@@ -102,3 +102,7 @@ opt_model = torch.compile(q_model)
 ```
 
 > Note: The `set_local` of `StaticQuantConfig` will be supported after the torch 2.4 release.
+
+#### Model Examples with PT2E
+
+Users could refer to [cv examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/cv/static_quant) and [llm examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/static_quant/pt2e) on how to quantize a new model.

docs/3x/PT_MXQuant.md

@@ -258,7 +258,7 @@ loaded_model = load(
 
 ## Examples
 
-Users can also refer to [examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/llm) on how to quantize a  model with WeightOnlyQuant.
+Users can also refer to [examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/weight_only) on how to quantize a  model with WeightOnlyQuant.
 
 ## Reference
 

docs/3x/PT_SmoothQuant.md

@@ -52,27 +52,15 @@ The following prerequisites and requirements must be satisfied for a successful
   pip install -i https://test.pypi.org/simple/ neural-compressor
   ```
 
-- Install from Conda 
-  ```Shell
-  # install on Linux OS
-  conda install opencv-python-headless -c fastai
-  conda install neural-compressor -c conda-forge -c intel
-  ```
-  ```Shell
-  # install on Windows OS
-  conda install pycocotools -c esri
-  conda install opencv-python-headless -c fastai
-  conda install neural-compressor -c conda-forge -c intel
-  ```
-
 ### Install from Source
 
   ```Shell
   git clone https://github.com/intel/neural-compressor.git
   cd neural-compressor
   pip install -r requirements.txt
-  # build with basic functionality
   python setup.py install
+  [optional] pip install requirements_pt.txt # for PyTorch framework extension API
+  [optional] pip install requirements_tf.txt # for TensorFlow framework extension API
   ```
 
 ### Install from AI Kit
@@ -112,7 +100,6 @@ The AI Kit is distributed through many common channels, including from Intel's w
   <tr style="vertical-align: middle; text-align: center;">
     <th>Framework</th>
     <th>TensorFlow</th>
-    <th>Intel<br>TensorFlow</th>
     <th>Intel®<br>Extension for<br>TensorFlow*</th>
     <th>PyTorch</th>
     <th>Intel®<br>Extension for<br>PyTorch*</th>
@@ -122,25 +109,26 @@ The AI Kit is distributed through many common channels, including from Intel's w
 <tbody>
   <tr align="center">
     <th>Version</th>
-    <td class="tg-7zrl"> <a href=https://github.com/tensorflow/tensorflow/tree/v2.15.0>2.15.0</a><br>
-    <a href=https://github.com/tensorflow/tensorflow/tree/v2.14.1>2.14.1</a><br>
-    <a href=https://github.com/tensorflow/tensorflow/tree/v2.13.1>2.13.1</a><br></td>
-    <td class="tg-7zrl"> <a href=https://github.com/Intel-tensorflow/tensorflow/tree/v2.14.0>2.14.0</a><br>
-    <a href=https://github.com/Intel-tensorflow/tensorflow/tree/v2.13.0>2.13.0</a><br></td>
-    <td class="tg-7zrl"> <a href=https://github.com/intel/intel-extension-for-tensorflow/tree/v2.14.0.1>2.14.0.1</a><br>
+    <td class="tg-7zrl">
+    <a href=https://github.com/tensorflow/tensorflow/tree/v2.16.1>2.16.1</a><br>
+    <a href=https://github.com/tensorflow/tensorflow/tree/v2.15.0>2.15.0</a><br>
+    <a href=https://github.com/tensorflow/tensorflow/tree/v2.14.1>2.14.1</a><br></td>
+    <td class="tg-7zrl"> 
+    <a href=https://github.com/intel/intel-extension-for-tensorflow/tree/v2.15.0.0>2.15.0.0</a><br>
+    <a href=https://github.com/intel/intel-extension-for-tensorflow/tree/v2.14.0.1>2.14.0.1</a><br>
     <a href=https://github.com/intel/intel-extension-for-tensorflow/tree/v2.13.0.0>2.13.0.0</a><br></td>
-    <td class="tg-7zrl"><a href=https://github.com/pytorch/pytorch/tree/v2.2.1>2.2.1</a><br>
-    <a href=https://github.com/pytorch/pytorch/tree/v2.1.0>2.1.0</a><br>
-    <a href=https://github.com/pytorch/pytorch/tree/v2.0.1>2.0.1</a><br></td>
-    <td class="tg-7zrl"><a href=https://github.com/intel/intel-extension-for-pytorch/tree/v2.2.0%2Bcpu>2.2.0</a><br>
-    <a href=https://github.com/intel/intel-extension-for-pytorch/tree/v2.1.100%2Bcpu>2.1.100</a><br>
-    <a href=https://github.com/intel/intel-extension-for-pytorch/tree/v2.0.100%2Bcpu>2.0.100</a><br></td>
-    <td class="tg-7zrl"><a href=https://github.com/microsoft/onnxruntime/tree/v1.17.1>1.17.1</a><br>
-    <a href=https://github.com/microsoft/onnxruntime/tree/v1.16.3>1.16.3</a><br>    
-    <a href=https://github.com/microsoft/onnxruntime/tree/v1.15.1>1.15.1</a><br></td>
+    <td class="tg-7zrl">
+    <a href=https://github.com/pytorch/pytorch/tree/v2.3.0>2.3.0</a><br>
+    <a href=https://github.com/pytorch/pytorch/tree/v2.2.2>2.2.2</a><br>
+    <a href=https://github.com/pytorch/pytorch/tree/v2.1.1>2.1.1</a><br></td>
+    <td class="tg-7zrl">
+    <a href=https://github.com/intel/intel-extension-for-pytorch/tree/v2.3.0%2Bcpu>2.3.0</a><br>
+    <a href=https://github.com/intel/intel-extension-for-pytorch/tree/v2.2.0%2Bcpu>2.2.0</a><br>
+    <a href=https://github.com/intel/intel-extension-for-pytorch/tree/v2.1.100%2Bcpu>2.1.100</a><br></td>
+    <td class="tg-7zrl">
+    <a href=https://github.com/microsoft/onnxruntime/tree/v1.18.0>1.18.0</a><br>
+    <a href=https://github.com/microsoft/onnxruntime/tree/v1.17.3>1.17.3</a><br>
+    <a href=https://github.com/microsoft/onnxruntime/tree/v1.16.3>1.16.3</a><br></td>
   </tr>
 </tbody>
 </table>
-
-> **Note:**
-> Set the environment variable ``TF_ENABLE_ONEDNN_OPTS=1`` to enable oneDNN optimizations if you are using TensorFlow before v2.9. oneDNN is the default for TensorFlow since [v2.9](https://github.com/tensorflow/tensorflow/releases/tag/v2.9.0) ([Intel Cascade Lake](https://www.intel.com/content/www/us/en/products/platforms/details/cascade-lake.html) and newer CPUs).