Update Neuronx-distributed llama3 example with newer NxD container im…

3.test_cases/pytorch/neuronx-distributed/llama3/kubernetes/Dockerfile

@@ -1,10 +1,13 @@
-FROM 763104351884.dkr.ecr.us-east-2.amazonaws.com/pytorch-training-neuronx:2.1.2-neuronx-py310-sdk2.19.1-ubuntu20.04
+FROM 763104351884.dkr.ecr.us-east-2.amazonaws.com/pytorch-training-neuronx:2.7.0-neuronx-py310-sdk2.24.1-ubuntu22.04
 
 RUN git clone https://github.com/aws-neuron/neuronx-distributed.git
 COPY ./src /workspace
+RUN cp -r neuronx-distributed/examples/training/llama/* workspace/
+RUN cp -r neuronx-distributed/examples/training/llama/tp_zero1_llama_hf_pretrain/* workspace/
 RUN cp -r neuronx-distributed/examples/training/llama/tp_zero1_llama_hf_pretrain/8B_config_llama3.1 workspace/config_8b_llama3.1
 RUN cp -r neuronx-distributed/examples/training/llama/tp_zero1_llama_hf_pretrain/8B_config_llama3 workspace/config_8b_llama3
+RUN mv workspace/tp_zero1_llama_hf_pretrain.py workspace/train.py
 
 WORKDIR /workspace
 
-RUN pip install -r requirements.txt
+RUN pip install -r requirements.txt

3.test_cases/pytorch/neuronx-distributed/llama3/kubernetes/README.md

@@ -36,7 +36,7 @@ region=us-east-2
 dlc_account_id=763104351884
 aws ecr get-login-password --region $region | docker login --username AWS --password-stdin $dlc_account_id.dkr.ecr.$region.amazonaws.com
 
-docker pull ${dlc_account_id}.dkr.ecr.${region}.amazonaws.com/pytorch-training-neuronx:2.1.2-neuronx-py310-sdk2.19.1-ubuntu20.04
+docker pull 763104351884.dkr.ecr.us-east-2.amazonaws.com/pytorch-training-neuronx:2.7.0-neuronx-py310-sdk2.24.1-ubuntu22.04
 ```
 
 ### Build Docker Image and push to ECR

3.test_cases/pytorch/neuronx-distributed/llama3/kubernetes/llama3_train.yaml-template

@@ -2,7 +2,6 @@ apiVersion: v1
 kind: Service
 metadata:
   name: etcd
-  namespace: kubeflow
 spec:
   ports:
     - name: etcd-client-port
@@ -19,7 +18,6 @@ metadata:
   labels:
     app: etcd
   name: etcd
-  namespace: kubeflow
 spec:
   replicas: 1
   selector:
@@ -57,7 +55,6 @@ apiVersion: "kubeflow.org/v1"
 kind: PyTorchJob
 metadata:
   name: trn1-llama3
-  namespace: kubeflow
 spec:
   elasticPolicy:
     rdzvBackend: etcd