diff --git a/Dockerfile.neuron b/Dockerfile.neuron
index 9550f5e3..5dafc355 100644
--- a/Dockerfile.neuron
+++ b/Dockerfile.neuron
@@ -153,14 +153,6 @@ COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/
 COPY --from=pyserver /pyserver/build/dist dist
 RUN pip install dist/text_generation_server*.tar.gz
 
-# AWS Sagemaker compatible image
-FROM neuron AS sagemaker
-
-COPY backends/neuron/sagemaker-entrypoint.sh entrypoint.sh
-RUN chmod +x entrypoint.sh
-
-ENTRYPOINT ["./entrypoint.sh"]
-
 # Final image
 FROM neuron
 
diff --git a/backends/neuron/sagemaker-entrypoint.sh b/backends/neuron/sagemaker-entrypoint.sh
deleted file mode 100644
index a8a6a730..00000000
--- a/backends/neuron/sagemaker-entrypoint.sh
+++ /dev/null
@@ -1,22 +0,0 @@
-#!/bin/bash
-
-if [[ -z "${HF_MODEL_ID}" ]]; then
-  echo "HF_MODEL_ID must be set"
-  exit 1
-fi
-export MODEL_ID="${HF_MODEL_ID}"
-
-if [[ -n "${HF_MODEL_REVISION}" ]]; then
-  export REVISION="${HF_MODEL_REVISION}"
-fi
-
-if [[ -n "${HF_MODEL_TRUST_REMOTE_CODE}" ]]; then
-  export TRUST_REMOTE_CODE="${HF_MODEL_TRUST_REMOTE_CODE}"
-fi
-
-if [[ -z "${MAX_BATCH_SIZE}" ]]; then
-  echo "MAX_BATCH_SIZE must be set to the model static batch size"
-  exit 1
-fi
-
-text-generation-launcher --port 8080