Add samples for LLM multi-host GPUs tutorials

ai-ml/llm-multihost-gpus/vllm-llama3-405b-A3.yaml

@@ -0,0 +1,131 @@
+# Copyright 2024 Google LLC
+#
+# 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.
+
+# [START gke_ai_ml_llm_serving_multihost_gpus_vllm_llama3_405b_a4]
+
+apiVersion: leaderworkerset.x-k8s.io/v1
+kind: LeaderWorkerSet
+metadata:
+  name: vllm
+spec:
+  replicas: 1
+  leaderWorkerTemplate:
+    size: 2
+    restartPolicy: RecreateGroupOnPodRestart
+    leaderTemplate:
+      metadata:
+        labels:
+          role: leader
+      spec:
+        containers:
+          - name: vllm-leader
+            image: us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20240821_1034_RC00
+            env:
+              - name: RAY_CLUSTER_SIZE
+                valueFrom:
+                  fieldRef:
+                    fieldPath: metadata.annotations['leaderworkerset.sigs.k8s.io/size']
+              - name: HUGGING_FACE_HUB_TOKEN
+            valueFrom:
+              secretKeyRef:
+                name: hf-secret
+                key: hf_api_token
+            command:
+              - sh
+              - -c
+              - "/workspace/vllm/examples/ray_init.sh leader --ray_cluster_size=$RAY_CLUSTER_SIZE; 
+                python3 -m vllm.entrypoints.api_server --port 8080 --model meta-llama/Meta-Llama-3.1-405B-Instruct --tensor-parallel-size 8 --pipeline-parallel-size 2"
+            resources:
+              limits:
+                nvidia.com/gpu: "8"
+                memory: 1124Gi
+                ephemeral-storage: 800Gi
+              requests:
+                ephemeral-storage: 800Gi
+                cpu: 125
+            ports:
+              - containerPort: 8080
+            readinessProbe:
+              tcpSocket:
+                port: 8080
+              initialDelaySeconds: 15
+              periodSeconds: 10
+            volumeMounts:
+              - mountPath: /dev/shm
+                name: dshm
+        volumes:
+        - name: dshm
+          emptyDir:
+            medium: Memory
+            sizeLimit: 15Gi
+    workerTemplate:
+      spec:
+        containers:
+          - name: vllm-worker
+            image: us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20240821_1034_RC00
+            command:
+              - sh
+              - -c
+              - "/workspace/vllm/examples/ray_init.sh worker --ray_address=$(LEADER_NAME).$(LWS_NAME).$(NAMESPACE).svc.cluster.local"
+            resources:
+              limits:
+                nvidia.com/gpu: "8"
+                memory: 1124Gi
+                ephemeral-storage: 800Gi
+              requests:
+                ephemeral-storage: 800Gi
+                cpu: 125
+            env:
+              - name: LEADER_NAME
+                valueFrom:
+                  fieldRef:
+                    fieldPath: metadata.annotations['leaderworkerset.sigs.k8s.io/leader-name']
+              - name: NAMESPACE
+                valueFrom:
+                  fieldRef:
+                    fieldPath: metadata.namespace
+              - name: LWS_NAME
+                valueFrom:
+                  fieldRef:
+                    fieldPath: metadata.labels['leaderworkerset.sigs.k8s.io/name']
+              - name: HUGGING_FACE_HUB_TOKEN
+            valueFrom:
+              secretKeyRef:
+                name: hf-secret
+                key: hf_api_token
+            volumeMounts:
+              - mountPath: /dev/shm
+                name: dshm   
+        volumes:
+        - name: dshm
+          emptyDir:
+            medium: Memory
+            sizeLimit: 15Gi
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: vllm-leader
+spec:
+  ports:
+    - name: http
+      port: 8080
+      protocol: TCP
+      targetPort: 8080
+  selector:
+    leaderworkerset.sigs.k8s.io/name: vllm
+    role: leader
+  type: ClusterIP
+
+  # [END gke_ai_ml_llm_serving_multihost_gpus_vllm_llama3_405b_a4]