diff --git a/docker/llm/serving/xpu/docker/Dockerfile b/docker/llm/serving/xpu/docker/Dockerfile
index fb346332..e4bfb1a4 100644
--- a/docker/llm/serving/xpu/docker/Dockerfile
+++ b/docker/llm/serving/xpu/docker/Dockerfile
@@ -53,7 +53,7 @@ RUN set -eux && \
     dpkg -i *.deb && \
     #
     # Install Intel PyTorch extension for LLM inference
-    pip install --pre --upgrade ipex-llm[xpu_2.6] --extra-index-url https://download.pytorch.org/whl/xpu && \
+    pip install --pre --upgrade ipex-llm[xpu_2.6]==2.3.0b20250407 --extra-index-url https://download.pytorch.org/whl/xpu && \
     #
     # Build torch-ccl
     mkdir -p /build && \
@@ -123,7 +123,7 @@ RUN set -eux && \
     wget https://bootstrap.pypa.io/get-pip.py -O get-pip.py && \
     python3 get-pip.py && rm get-pip.py && \
     pip install --upgrade requests argparse urllib3 && \
-    pip install --pre --upgrade ipex-llm[xpu_2.6] --extra-index-url https://download.pytorch.org/whl/xpu && \
+    pip install --pre --upgrade ipex-llm[xpu_2.6]==2.3.0b20250407 --extra-index-url https://download.pytorch.org/whl/xpu && \
     pip install transformers_stream_generator einops tiktoken && \
     pip install --upgrade colorama && \
     # 
diff --git a/docker/llm/serving/xpu/docker/vllm_for_multi_arc.patch b/docker/llm/serving/xpu/docker/vllm_for_multi_arc.patch
index 672ad407..7e4c62d6 100644
--- a/docker/llm/serving/xpu/docker/vllm_for_multi_arc.patch
+++ b/docker/llm/serving/xpu/docker/vllm_for_multi_arc.patch
@@ -12211,6 +12211,19 @@ index 000000000..75a99ffc1
 +# Pass the collected arguments to the main entrypoint
 +exec python3 -m vllm.entrypoints.openai.api_server "${ARGS[@]}"
 \ No newline at end of file
+diff --git a/requirements-common.txt b/requirements-common.txt
+index 6c390bcfd..b22364c5a 100644
+--- a/requirements-common.txt
++++ b/requirements-common.txt
+@@ -21,7 +21,7 @@ tiktoken >= 0.6.0  # Required for DBRX tokenizer
+ lm-format-enforcer >= 0.10.9, < 0.11
+ outlines == 0.1.11 # Requires pytorch
+ lark == 1.2.2 
+-xgrammar >= 0.1.6; platform_machine == "x86_64"
++xgrammar <= 0.1.17; platform_machine == "x86_64"
+ typing_extensions >= 4.10
+ filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
+ partial-json-parser # used for parsing partial JSON outputs
 diff --git a/requirements-neuron.txt b/requirements-neuron.txt
 index 148fdbe0d..5e08d101f 100644
 --- a/requirements-neuron.txt