chore: remove stale example assets (#7059)

examples/basics/kubernetes/shared_frontend/README.md

-# Shared Dynamo Frontend
-This folder contains kubernetes manifests to deploy Dynamo frontend component as a standalone DynamoGraphDeployment (DGD)
-and two models.
-Frontend is shared across the two models. Frontend is deployed to  dynamo namespace `dynamo`, which is a reserved namespace name for frontend to observe deployed models across all dynamo namespaces.
-A shared PVC is configured to store model checkpoint weights fetched from Hugging Face.
-
-1. Install Dynamo k8s platform helm chart
-2. Create a K8S secret with your Huggingface token and then render k8s manifests
-```sh
-export HF_TOKEN=YOUR_HF_TOKEN
-kubectl create secret generic hf-token-secret \
-    --from-literal=HF_TOKEN=${HF_TOKEN} \
-    --namespace ${NAMESPACE}
-kubectl apply -f shared_frontend.yaml --namespace ${NAMESPACE}
-```
-3. Testing the deployment and run benchmarks
-After deployment, forward the frontend service to access the API:
-```sh
-kubectl port-forward svc/frontend-frontend 8000:8000 -n ${NAMESPACE}
-```
-confirm both deployed models are present in the model listing:
-```sh
-curl localhost:8000/v1/models
-{"object":"list","data":[{"id":"Qwen/Qwen3-0.6B","object":"object","created":1759458713,"owned_by":"nvidia"},{"id":"Qwen/Qwen2.5-VL-7B-Instruct","object":"object","created":1759458718,"owned_by":"nvidia"}]}
-```
-and use following request to test one of the deployed model
-```sh
-curl localhost:8000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "Qwen/Qwen3-0.6B",
-    "messages": [
-    {
-        "role": "user",
-        "content": "In the heart of Eldoria, an ancient land of boundless magic and mysterious creatures, lies the long-forgotten city of Aeloria. Once a beacon of knowledge and power, Aeloria was buried beneath the shifting sands of time, lost to the world for centuries. You are an intrepid explorer, known for your unparalleled curiosity and courage, who has stumbled upon an ancient map hinting at ests that Aeloria holds a secret so profound that it has the potential to reshape the very fabric of reality. Your journey will take you through treacherous deserts, enchanted forests, and across perilous mountain ranges. Your Task: Character Background: Develop a detailed background for your character. Describe their motivations for seeking out Aeloria, their skills and weaknesses, and any personal connections to the ancient city or its legends. Are they driven by a quest for knowledge, a search for lost familt clue is hidden."
-    }
-    ],
-    "stream": false,
-    "max_tokens": 30
-  }'
-  ```
-You can also benchmark the performance of the endpoint by [AIPerf](https://github.com/ai-dynamo/aiperf/blob/main/README.md)

examples/basics/kubernetes/shared_frontend/shared_frontend.yaml

-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: dynamo-model-cache
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 100Gi
----
-apiVersion: nvidia.com/v1alpha1
-kind: DynamoGraphDeployment
-metadata:
-  name: frontend
-spec:
-  services:
-    Frontend:
-      componentType: frontend
-      globalDynamoNamespace: true
-      replicas: 1
-      extraPodSpec:
-        mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
----
-apiVersion: nvidia.com/v1alpha1
-kind: DynamoGraphDeployment
-metadata:
-  name: vllm-agg
-spec:
-  pvcs:
-  - name: dynamo-model-cache
-    create: false
-  services:
-    VllmDecodeWorker:
-      volumeMounts:
-      - name: dynamo-model-cache
-        mountPoint: /root/.cache/huggingface
-      envFromSecret: hf-token-secret
-      componentType: worker
-      replicas: 1
-      resources:
-        limits:
-          gpu: "1"
-      extraPodSpec:
-        mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
-          workingDir: /workspace/examples/backends/vllm
-          command:
-            - /bin/sh
-            - -c
-          args:
-            - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B
----
-apiVersion: nvidia.com/v1alpha1
-kind: DynamoGraphDeployment
-metadata:
-  name: agg-qwen
-spec:
-  backendFramework: vllm
-  services:
-    EncodeWorker:
-      volumeMounts:
-      - name: dynamo-model-cache
-        mountPoint: /root/.cache/huggingface
-      envFromSecret: hf-token-secret
-      componentType: worker
-      replicas: 1
-      resources:
-        limits:
-          gpu: "1"
-      extraPodSpec:
-        mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
-          workingDir: /workspace/examples/multimodal
-          command:
-            - /bin/sh
-            - -c
-          args:
-            - python3 components/encode_worker.py --model Qwen/Qwen2.5-VL-7B-Instruct
-    VLMWorker:
-      volumeMounts:
-      - name: dynamo-model-cache
-        mountPoint: /root/.cache/huggingface
-      envFromSecret: hf-token-secret
-      componentType: worker
-      replicas: 1
-      resources:
-        limits:
-          gpu: "1"
-      extraPodSpec:
-        mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
-          workingDir: /workspace/examples/multimodal
-          command:
-            - /bin/sh
-            - -c
-          args:
-            - python3 components/worker.py --model Qwen/Qwen2.5-VL-7B-Instruct --worker-type prefill
-    Processor:
-      volumeMounts:
-      - name: dynamo-model-cache
-        mountPoint: /root/.cache/huggingface
-      envFromSecret: hf-token-secret
-      componentType: worker
-      replicas: 1
-      resources:
-        limits:
-          gpu: "1"
-      extraPodSpec:
-        mainContainer:
-          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.5.0
-          workingDir: /workspace/examples/multimodal
-          command:
-            - /bin/sh
-            - -c
-          args:
-            - 'python3 components/processor.py --model Qwen/Qwen2.5-VL-7B-Instruct --prompt-template "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|><prompt><|im_end|>\n<|im_start|>assistant\n"'

examples/basics/multinode/trtllm/README.md

-<!--
-SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-SPDX-License-Identifier: Apache-2.0
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
--->
-
-# Example: Multi-node TRTLLM Workers with Dynamo on Slurm
-
-See [here](/docs/backends/trtllm/multinode) for how to setup this example.

examples/basics/multinode/trtllm/srun_aggregated.sh

-#!/bin/bash
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-# This is one of the only variables that must be set currently, most of the rest may
-# just work out of the box if following the steps in the README.
-IMAGE="${IMAGE:-""}"
-
-# Set to mount current host directory to /mnt inside the container as an example,
-# but you may freely customize the mounts based on your cluster. A common practice
-# is to mount paths to NFS storage for common scripts, model weights, etc.
-# NOTE: This can be a comma separated list of multiple mounts as well.
-DEFAULT_MOUNT="${PWD}/../../../../:/mnt"
-MOUNTS="${MOUNTS:-${DEFAULT_MOUNT}}"
-
-# Example values, assuming 4 nodes with 4 GPUs on each node, such as 4xGB200 nodes.
-# For 8xH100 nodes as an example, you may set this to 2 nodes x 8 gpus/node instead.
-NUM_NODES=${NUM_NODES:-4}
-NUM_GPUS_PER_NODE=${NUM_GPUS_PER_NODE:-4}
-
-export ENGINE_CONFIG="${ENGINE_CONFIG:-/mnt/examples/backends/trtllm/engine_configs/deepseek-r1/agg/wide_ep/wide_ep_agg.yaml}"
-
-# Automate settings of certain variables for convenience, but you are free
-# to manually set these for more control as well.
-ACCOUNT="$(sacctmgr -nP show assoc where user=$(whoami) format=account)"
-export HEAD_NODE="${SLURMD_NODENAME}"
-export HEAD_NODE_IP="$(hostname -i)"
-export ETCD_ENDPOINTS="${HEAD_NODE_IP}:2379"
-export NATS_SERVER="nats://${HEAD_NODE_IP}:4222"
-
-if [[ -z ${IMAGE} ]]; then
-  echo "ERROR: You need to set the IMAGE environment variable to the " \
-       "Dynamo+TRTLLM docker image or .sqsh file from 'enroot import' " \
-       "See how to build one from source here: " \
-       "https://github.com/ai-dynamo/dynamo/tree/main/docs/backends/trtllm/README.md#build-container"
-  exit 1
-fi
-
-# NOTE: Output streamed to stdout for ease of understanding the example, but
-# in practice you would probably set `srun --output ... --error ...` to pipe
-# the stdout/stderr to files.
-echo "Launching frontend services in background."
-srun \
-  --mpi pmix \
-  --overlap \
-  --container-image "${IMAGE}" \
-  --container-mounts "${MOUNTS}" \
-  --verbose \
-  --label \
-  -A "${ACCOUNT}" \
-  -J "${ACCOUNT}-dynamo.trtllm" \
-  --nodelist "${HEAD_NODE}" \
-  --nodes 1 \
-  --jobid "${SLURM_JOB_ID}" \
-  /mnt/examples/basics/multinode/trtllm/start_frontend_services.sh &
-
-# NOTE: Output streamed to stdout for ease of understanding the example, but
-# in practice you would probably set `srun --output ... --error ...` to pipe
-# the stdout/stderr to files.
-echo "Launching multi-node worker in background."
-DISAGGREGATION_MODE="prefill_and_decode" \
-srun \
-  --mpi pmix \
-  --oversubscribe \
-  --container-image "${IMAGE}" \
-  --container-mounts "${MOUNTS}" \
-  --container-env ETCD_ENDPOINTS,NATS_SERVER,HEAD_NODE_IP,HEAD_NODE,DISAGGREGATION_MODE,ENGINE_CONFIG \
-  --verbose \
-  --label \
-  -A "${ACCOUNT}" \
-  -J "${ACCOUNT}-dynamo.trtllm" \
-  --nodes "${NUM_NODES}" \
-  --ntasks-per-node "${NUM_GPUS_PER_NODE}" \
-  --jobid "${SLURM_JOB_ID}" \
-  /mnt/examples/basics/multinode/trtllm/start_trtllm_worker.sh &

examples/basics/multinode/trtllm/srun_disaggregated.sh

-#!/bin/bash
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-# This is one of the only variables that must be set currently, most of the rest may
-# just work out of the box if following the steps in the README.
-IMAGE="${IMAGE:-""}"
-
-# Set to mount current host directory to /mnt inside the container as an example,
-# but you may freely customize the mounts based on your cluster. A common practice
-# is to mount paths to NFS storage for common scripts, model weights, etc.
-# NOTE: This can be a comma separated list of multiple mounts as well.
-DEFAULT_MOUNT="${PWD}/../../../../:/mnt"
-MOUNTS="${MOUNTS:-${DEFAULT_MOUNT}}"
-
-NUM_GPUS_PER_NODE=${NUM_GPUS_PER_NODE:-4}
-
-NUM_PREFILL_NODES=${NUM_PREFILL_NODES:-4}
-NUM_PREFILL_WORKERS=${NUM_PREFILL_WORKERS:-1}
-PREFILL_ENGINE_CONFIG="${PREFILL_ENGINE_CONFIG:-/mnt/examples/backends/trtllm/engine_configs/deepseek-r1/disagg/wide_ep/wide_ep_prefill.yaml}"
-
-NUM_DECODE_NODES=${NUM_DECODE_NODES:-4}
-NUM_DECODE_WORKERS=${NUM_DECODE_WORKERS:-1}
-DECODE_ENGINE_CONFIG="${DECODE_ENGINE_CONFIG:-/mnt/examples/backends/trtllm/engine_configs/deepseek-r1/disagg/wide_ep/wide_ep_decode.yaml}"
-
-# Automate settings of certain variables for convenience, but you are free
-# to manually set these for more control as well.
-ACCOUNT="$(sacctmgr -nP show assoc where user=$(whoami) format=account)"
-export HEAD_NODE="${SLURMD_NODENAME}"
-export HEAD_NODE_IP="$(hostname -i)"
-export ETCD_ENDPOINTS="${HEAD_NODE_IP}:2379"
-export NATS_SERVER="nats://${HEAD_NODE_IP}:4222"
-
-if [[ -z ${IMAGE} ]]; then
-  echo "ERROR: You need to set the IMAGE environment variable to the " \
-       "Dynamo+TRTLLM docker image or .sqsh file from 'enroot import' " \
-       "See how to build one from source here: " \
-       "https://github.com/ai-dynamo/dynamo/tree/main/docs/backends/trtllm/README.md#build-container"
-  exit 1
-fi
-
-# NOTE: Output streamed to stdout for ease of understanding the example, but
-# in practice you would probably set `srun --output ... --error ...` to pipe
-# the stdout/stderr to files.
-echo "Launching frontend services in background."
-srun \
-  --mpi pmix \
-  --overlap \
-  --container-image "${IMAGE}" \
-  --container-mounts "${MOUNTS}" \
-  --verbose \
-  --label \
-  -A "${ACCOUNT}" \
-  -J "${ACCOUNT}-dynamo.trtllm" \
-  --nodelist "${HEAD_NODE}" \
-  --nodes 1 \
-  --jobid "${SLURM_JOB_ID}" \
-  /mnt/examples/basics/multinode/trtllm/start_frontend_services.sh &
-
-# NOTE: Output streamed to stdout for ease of understanding the example, but
-# in practice you would probably set `srun --output ... --error ...` to pipe
-# the stdout/stderr to files.
-for ((i=1; i<=${NUM_PREFILL_WORKERS}; i++)); do
-  echo "Launching multi-node prefill worker in background."
-  DISAGGREGATION_MODE=prefill \
-  ENGINE_CONFIG=${PREFILL_ENGINE_CONFIG} \
-  srun \
-    --mpi pmix \
-    --oversubscribe \
-    --container-image "${IMAGE}" \
-    --container-mounts "${MOUNTS}" \
-    --container-env ETCD_ENDPOINTS,NATS_SERVER,HEAD_NODE_IP,HEAD_NODE,DISAGGREGATION_MODE,ENGINE_CONFIG \
-    --verbose \
-    --label \
-    -A "${ACCOUNT}" \
-    -J "${ACCOUNT}-dynamo.trtllm" \
-    --nodes "${NUM_PREFILL_NODES}" \
-    --ntasks-per-node "${NUM_GPUS_PER_NODE}" \
-    --jobid "${SLURM_JOB_ID}" \
-    /mnt/examples/basics/multinode/trtllm/start_trtllm_worker.sh &
-done
-
-for ((i=1; i<=${NUM_DECODE_WORKERS}; i++)); do
-  echo "Launching multi-node decode worker in background."
-  DISAGGREGATION_MODE=decode \
-  ENGINE_CONFIG=${DECODE_ENGINE_CONFIG} \
-  srun \
-    --mpi pmix \
-    --oversubscribe \
-    --container-image "${IMAGE}" \
-    --container-mounts "${MOUNTS}" \
-    --container-env ETCD_ENDPOINTS,NATS_SERVER,HEAD_NODE_IP,HEAD_NODE,DISAGGREGATION_MODE,ENGINE_CONFIG \
-    --verbose \
-    --label \
-    -A "${ACCOUNT}" \
-    -J "${ACCOUNT}-dynamo.trtllm" \
-    --nodes "${NUM_DECODE_NODES}" \
-    --ntasks-per-node "${NUM_GPUS_PER_NODE}" \
-    --jobid "${SLURM_JOB_ID}" \
-    /mnt/examples/basics/multinode/trtllm/start_trtllm_worker.sh &
-done

examples/basics/multinode/trtllm/start_frontend_services.sh

-#!/bin/bash
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-# Start NATS
-nats-server -js &
-
-# Start etcd
-etcd --listen-client-urls http://0.0.0.0:2379 --advertise-client-urls http://0.0.0.0:2379 --data-dir /tmp/etcd &
-
-# Wait for NATS/etcd to startup
-sleep 3
-
-# Start OpenAI Frontend which will dynamically discover workers when they startup
-# dynamo.frontend accepts either --http-port flag or DYN_HTTP_PORT env var (defaults to 8000)
-# NOTE: This is a blocking call.
-python3 -m dynamo.frontend