update main page (#1973)

Signed-off-by: chensuyue <[email protected]>

Author: chensuyue

.azure-pipelines/scripts/ut/run_itrex.sh

@@ -19,6 +19,8 @@ sed -i '/neural-compressor.git/d' /intel-extension-for-transformers/tests/requir
 pip install -r /intel-extension-for-transformers/tests/requirements.txt
 # workaround
 pip install onnx==1.15.0
+echo "pip list itrex ut deps..."
+pip list
 LOG_DIR=/neural-compressor/log_dir
 mkdir -p ${LOG_DIR}
 ut_log_name=${LOG_DIR}/ut_itrex.log

.azure-pipelines/ut-3x-pt-fp8.yml

@@ -41,7 +41,7 @@ stages:
               dockerConfigName: "commonDockerConfig"
               utScriptFileName: "3x/run_3x_pt_fp8"
               uploadPath: $(UPLOAD_PATH)
-              utArtifact: "ut_3x_pt_fp8"
+              utArtifact: "ut_3x"
 
   - stage: Torch_habana_baseline
     displayName: Torch 3x Habana FP8 baseline
@@ -56,7 +56,7 @@ stages:
               dockerConfigName: "gitCloneDockerConfig"
               utScriptFileName: "3x/run_3x_pt_fp8"
               uploadPath: $(UPLOAD_PATH)
-              utArtifact: "ut_3x_pt_fp8_baseline"
+              utArtifact: "ut_3x_baseline"
 
   - stage: Coverage
     displayName: "Coverage Compare"

README.md

@@ -2,7 +2,7 @@
 
 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>
+<h3> An open-source Python library supporting popular model compression techniques on all mainstream deep learning frameworks (TensorFlow, PyTorch, and ONNX Runtime)</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-3.0-green)](https://github.com/intel/neural-compressor/releases)
@@ -15,7 +15,7 @@ Intel® Neural Compressor
 ---
 <div align="left">
 
-Intel® Neural Compressor aims to provide popular model compression techniques such as quantization, pruning (sparsity), distillation, and neural architecture search on mainstream frameworks such as [TensorFlow](https://www.tensorflow.org/), [PyTorch](https://pytorch.org/), [ONNX Runtime](https://onnxruntime.ai/), and [MXNet](https://mxnet.apache.org/),
+Intel® Neural Compressor aims to provide popular model compression techniques such as quantization, pruning (sparsity), distillation, and neural architecture search on mainstream frameworks such as [TensorFlow](https://www.tensorflow.org/), [PyTorch](https://pytorch.org/), and [ONNX Runtime](https://onnxruntime.ai/),
 as well as Intel extensions such as [Intel Extension for TensorFlow](https://github.com/intel/intel-extension-for-tensorflow) and [Intel Extension for PyTorch](https://github.com/intel/intel-extension-for-pytorch).
 In particular, the tool provides the key features, typical examples, and open collaborations as below:
 

docs/source/CONTRIBUTING.md

@@ -51,7 +51,7 @@ And generally use [Azure Cloud Instance](https://azure.microsoft.com/en-us/prici
 |     Code Scan                 |     Bandit/CopyRight/DocStyle/SpellCheck       |     PASS          |
 |     [DCO](https://github.com/apps/dco/)     |     Use `git commit -s` to sign off     |     PASS          |
 |     Unit Test                 |     Pytest scripts under [test](/test)                |      PASS (No failure, No core dump, No segmentation fault, No coverage drop)      |
-|     Model Test                |     Pytorch + TensorFlow + ONNX Runtime + MXNet         |      PASS (Functionality pass, FP32/INT8 No performance regression)       |
+|     Model Test                |     Pytorch + TensorFlow + ONNX Runtime         |      PASS (Functionality pass, FP32/INT8 No performance regression)       |
 
 ## Support