Fix PSIRT Vulnerability - Dependency Confusion in oneccl_bind_pt package (#5226)

* Update Dockerfile

* Update README.md

* Update README.md

* Update README.md

Author: liu-shaojun

docker/llm/inference/cpu/docker/Dockerfile

@@ -57,7 +57,7 @@ RUN env DEBIAN_FRONTEND=noninteractive apt-get update && \
     pip install Jinja2==3.1.3 && \
     pip install torch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 --index-url https://download.pytorch.org/whl/cpu && \
     pip install intel-extension-for-pytorch==2.2.0 && \
-    pip install oneccl_bind_pt==2.2.0 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
+    pip install oneccl_bind_pt==2.2.0 --index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
     pip install transformers==4.36.2
 
 ENTRYPOINT ["/bin/bash"]

python/llm/example/CPU/Speculative-Decoding/baichuan2/README.md

@@ -69,7 +69,7 @@ To accelerate speculative decoding on CPU, optionally, you can install our valid
 ```bash
 python -m pip install torch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 --index-url https://download.pytorch.org/whl/cpu
 python -m pip install intel-extension-for-pytorch==2.2.0
-python -m pip install oneccl_bind_pt==2.2.0 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
+python -m pip install oneccl_bind_pt==2.2.0 --index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
 # if there is any installation problem for oneccl_binding, you can also find suitable index url at "https://pytorch-extension.intel.com/release-whl/stable/cpu/cn/" or "https://developer.intel.com/ipex-whl-stable-cpu" according to your environment.
 
 # Install other dependencies

python/llm/example/CPU/Speculative-Decoding/llama2/README.md

@@ -104,7 +104,7 @@ To accelerate speculative decoding on CPU, you can install our validated version
 # Install IPEX 2.2.0+cpu
 python -m pip install torch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 --index-url https://download.pytorch.org/whl/cpu
 python -m pip install intel-extension-for-pytorch==2.2.0
-python -m pip install oneccl_bind_pt==2.2.0 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
+python -m pip install oneccl_bind_pt==2.2.0 --index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
 # if there is any installation problem for oneccl_binding, you can also find suitable index url at "https://pytorch-extension.intel.com/release-whl/stable/cpu/cn/" or "https://developer.intel.com/ipex-whl-stable-cpu" according to your environment.
 
 # Update transformers

python/llm/example/CPU/Speculative-Decoding/mistral/README.md

@@ -90,7 +90,7 @@ To accelerate speculative decoding on CPU, you can install our validated version
 # Install IPEX 2.2.0+cpu
 python -m pip install torch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 --index-url https://download.pytorch.org/whl/cpu
 python -m pip install intel-extension-for-pytorch==2.2.0
-python -m pip install oneccl_bind_pt==2.2.0 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
+python -m pip install oneccl_bind_pt==2.2.0 --index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
 # if there is any installation problem for oneccl_binding, you can also find suitable index url at "https://pytorch-extension.intel.com/release-whl/stable/cpu/cn/" or "https://developer.intel.com/ipex-whl-stable-cpu" according to your environment.
 
 # Update transformers