diff --git a/Dockerfile_intel b/Dockerfile_intel
index bc9071b8..e7144c76 100644
--- a/Dockerfile_intel
+++ b/Dockerfile_intel
@@ -118,8 +118,8 @@ ENV CCL_ZE_IPC_EXCHANGE=sockets
 #ENV TORCH_LLM_ALLREDUCE=1
 #ENV CCL_TOPO_FABRIC_VERTEX_CONNECTION_CHECK=0
 
-RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout c3e14caf792ad04824dd921e2fc3f16fca0d462e
-RUN cd intel-extension-for-pytorch && git submodule update --init --recursive && USE_AOT_DEVLIST='pvc' BUILD_SEPARATE_OPS=OFF BUILD_WITH_CPU=OFF USE_XETLA=ON python setup.py install && rm -rf /usr/src/intel-extension-for-pytorch
+RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout 033af6f63745ac748cccdadee5c6140c7971edf6
+RUN cd intel-extension-for-pytorch && git submodule update --init --recursive && USE_AOT_DEVLIST='pvc,ats-m150' BUILD_SEPARATE_OPS=OFF BUILD_WITH_CPU=OFF USE_XETLA=ON python setup.py install && rm -rf /usr/src/intel-extension-for-pytorch
 
 # Install benchmarker
 COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
diff --git a/README.md b/README.md
index 6d3a9b12..31966ddb 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 <div align="center">
 
 <a href="https://www.youtube.com/watch?v=jlMAX2Oaht0">
-  <img width=560 width=315 alt="Making TGI deployment optimal" src="https://huggingface.co/datasets/Narsil/tgi_assets/resolve/main/thumbnail.png">
+  <img width=560 alt="Making TGI deployment optimal" src="https://huggingface.co/datasets/Narsil/tgi_assets/resolve/main/thumbnail.png">
 </a>
 
 # Text Generation Inference
@@ -141,8 +141,8 @@ You have the option to utilize the `HF_TOKEN` environment variable for configuri
 For example, if you want to serve the gated Llama V2 model variants:
 
 1. Go to https://huggingface.co/settings/tokens
-2. Copy your cli READ token
-3. Export `HF_TOKEN=<your cli READ token>`
+2. Copy your CLI READ token
+3. Export `HF_TOKEN=<your CLI READ token>`
 
 or with Docker:
 
@@ -157,7 +157,7 @@ docker run --gpus all --shm-size 1g -e HF_TOKEN=$token -p 8080:80 -v $volume:/da
 ### A note on Shared Memory (shm)
 
 [`NCCL`](https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/index.html) is a communication framework used by
-`PyTorch` to do distributed training/inference. `text-generation-inference` make
+`PyTorch` to do distributed training/inference. `text-generation-inference` makes
 use of `NCCL` to enable Tensor Parallelism to dramatically speed up inference for large language models.
 
 In order to share data between the different devices of a `NCCL` group, `NCCL` might fall back to using the host memory if
@@ -196,7 +196,7 @@ Detailed blogpost by Adyen on TGI inner workings: [LLM inference at scale with T
 
 You can also opt to install `text-generation-inference` locally.
 
-First clone the repository and change directoy into it:
+First clone the repository and change directory into it:
 
 ```shell
 git clone https://github.com/huggingface/text-generation-inference
@@ -213,7 +213,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
 conda create -n text-generation-inference python=3.11
 conda activate text-generation-inference
 
-#using pyton venv
+#using python venv
 python3 -m venv .venv
 source .venv/bin/activate
 ```
diff --git a/router/src/kserve.rs b/router/src/kserve.rs
index c53fa481..ea85eb8c 100644
--- a/router/src/kserve.rs
+++ b/router/src/kserve.rs
@@ -205,6 +205,7 @@ pub async fn kserve_model_infer(
             let generate_request = GenerateRequest {
                 inputs: str_input.to_string(),
                 parameters: payload.parameters.clone(),
+                add_special_tokens: true,
             };
             let infer = infer.clone();
             let compute_type = compute_type.clone();
@@ -212,7 +213,7 @@ pub async fn kserve_model_infer(
             async move {
                 generate_internal(infer, compute_type, Json(generate_request), span)
                     .await
-                    .map(|(_, Json(generation))| {
+                    .map(|(_, _, Json(generation))| {
                         let generation_as_bytes = generation.generated_text.as_bytes().to_vec();
                         OutputChunk {
                             name: output.name.clone(),