format update (#3764)

* format update

* add wheel package installation

* llm env setup BKC for release version

Author: ZailiWang

docs/design_doc/cpu/isa_dyndisp.md

@@ -1154,7 +1154,8 @@ def construct_model(args):
     # the optimizer update will be applied in the backward pass, in this case through a fused op.
     # TorchRec will use the FBGEMM implementation of EXACT_ADAGRAD.
     # For GPU devices, a fused CUDA kernel is invoked. For CPU, FBGEMM_GPU invokes CPU kernels
-    # https://github.com/pytorch/FBGEMM/blob/2cb8b0dff3e67f9a009c4299defbd6b99cc12b8f/fbgemm_gpu/fbgemm_gpu/split_table_batched_embeddings_ops.py#L676-L678
+    # https://github.com/pytorch/FBGEMM/blob/2cb8b0dff3e67f9a009c4299defbd6b99cc12b8f
+    #     /fbgemm_gpu/fbgemm_gpu/split_table_batched_embeddings_ops.py#L676-L678
 
     # Note that lr_decay, weight_decay and initial_accumulator_value for Adagrad optimizer in FBGEMM v0.3.2
     # cannot be specified below. This equivalently means that all these parameters are hardcoded to zero.

docs/tutorials/features/optimizer_fusion.md

@@ -7,40 +7,84 @@ And a set of data types are supported for various scenarios, including FP32, BF1
 
 # 2. Environment Setup
 
-**Note**: The instructions in this section will setup an environment with a recent PyTorch\* nightly build and **a latest source build of IPEX**. 
-If you would like to use stable PyTorch\* and IPEX release versions, please refer to the instructions [in the release branch](https://github.com/intel/intel-extension-for-pytorch/blob/v2.7.0%2Bcpu/examples/cpu/llm/README.md#2-environment-setup),
-in which IPEX is installed via prebuilt wheels using `pip install` rather than source code building.
+## 2.1 [RECOMMENDED] Docker-based environment setup with pre-built wheels
 
-## 2.1 [Recommended] Docker-based environment setup with compilation from source
+```bash
+# Get the Intel® Extension for PyTorch\* source code
+git clone https://github.com/intel/intel-extension-for-pytorch.git
+cd intel-extension-for-pytorch
+git checkout v2.8.0+cpu
+git submodule sync
+git submodule update --init --recursive
+
+# Build an image with the provided Dockerfile by installing from Intel® Extension for PyTorch\* prebuilt wheel files
+# To have a custom ssh server port for multi-nodes run, please add --build-arg PORT_SSH=<CUSTOM_PORT> ex: 2345, otherwise use the default 22 SSH port
+DOCKER_BUILDKIT=1 docker build -f examples/cpu/llm/Dockerfile --build-arg PORT_SSH=2345 -t ipex-llm:2.8.0 .
+
+# Run the container with command below
+docker run --rm -it --privileged -v /dev/shm:/dev/shm ipex-llm:2.8.0 bash
+
+# When the command prompt shows inside the docker container, enter llm examples directory
+cd llm
+
+# Activate environment variables
+source ./tools/env_activate.sh inference
+```
+
+## 2.2 Conda-based environment setup with pre-built wheels
+
+```bash
+# Get the Intel® Extension for PyTorch\* source code
+git clone https://github.com/intel/intel-extension-for-pytorch.git
+cd intel-extension-for-pytorch
+git checkout v2.8.0+cpu
+git submodule sync
+git submodule update --init --recursive
+
+# GCC 12.3 is required. Installation can be taken care of by the environment configuration script.
+# Create a conda environment
+conda create -n llm python=3.10 -y
+conda activate llm
+
+# Setup the environment with the provided script
+cd examples/cpu/llm
+bash ./tools/env_setup.sh 7
+
+# Activate environment variables
+source ./tools/env_activate.sh inference
+```
+
+## 2.3 Docker-based environment setup with compilation from source
 
 ```bash
 # Get the Intel® Extension for PyTorch\* source code
 git clone https://github.com/intel/intel-extension-for-pytorch.git
 cd intel-extension-for-pytorch
+git checkout v2.8.0+cpu
 git submodule sync
 git submodule update --init --recursive
 
 # Build an image with the provided Dockerfile by compiling Intel® Extension for PyTorch\* from source
 # To have a custom ssh server port for multi-nodes run, please add --build-arg PORT_SSH=<CUSTOM_PORT> ex: 2345, otherwise use the default 22 SSH port
-docker build -f examples/cpu/llm/Dockerfile --build-arg COMPILE=ON --build-arg PORT_SSH=2345 -t ipex-llm:main .
+docker build -f examples/cpu/llm/Dockerfile --build-arg COMPILE=ON --build-arg PORT_SSH=2345 -t ipex-llm:2.8.0 .
 
 # Run the container with command below
-docker run --rm -it --net host --privileged -v /dev/shm:/dev/shm ipex-llm:main bash
+docker run --rm -it --net host --privileged -v /dev/shm:/dev/shm ipex-llm:2.8.0 bash
 
 # When the command prompt shows inside the docker container, enter llm examples directory
 cd llm
 
 # Activate environment variables
-# set bash script argument to "inference" or "fine-tuning" for different usages
 source ./tools/env_activate.sh inference
 ```
 
-## 2.2 Conda-based environment setup with compilation from source
+## 2.4 Conda-based environment setup with compilation from source
 
 ```bash
 # Get the Intel® Extension for PyTorch\* source code
 git clone https://github.com/intel/intel-extension-for-pytorch.git
 cd intel-extension-for-pytorch
+git checkout v2.8.0+cpu
 git submodule sync
 git submodule update --init --recursive
 
@@ -54,7 +98,6 @@ cd examples/cpu/llm
 bash ./tools/env_setup.sh 3
 
 # Activate environment variables
-# set bash script argument to "inference" or "fine-tuning" for different usages
 source ./tools/env_activate.sh inference
 ```
 

docs/tutorials/features/split_sgd.rst

@@ -69,7 +69,7 @@ if [ $((${MODE} & 0x02)) -ne 0 ]; then
     mkdir ${WHEELFOLDER}
 
     # Install deps
-    python -m pip install cmake==3.28.4 ninja
+    python -m pip install cmake==3.28.4 ninja wheel
 
     echo "#!/bin/bash" > ${AUX_INSTALL_SCRIPT}
     if [ $((${MODE} & 0x04)) -ne 0 ]; then