dearsky/wifi-densepose
1
0
Fork 0
Code Issues 20 Pull Requests 5 Actions Packages Projects Releases 1 Wiki Activity

Squashed 'vendor/ruvector/' content from commit b64c2172

Browse Source 
git-subtree-dir: vendor/ruvector
git-subtree-split: b64c21726f2bb37286d9ee36a7869fef60cc6900
This commit is contained in:
ruv
2026-02-28 14:39:40 -05:00
commit d803bfe2b1
7854 changed files with 3522914 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

277
examples/google-cloud/cloudrun.yaml Normal file
View File

@@ -0,0 +1,277 @@
# =============================================================================
# RuVector Cloud Run Service Configuration
# Multi-service deployment with GPU, Raft, and Replication support
# =============================================================================
# -----------------------------------------------------------------------------
# Benchmark Service (GPU-enabled)
# -----------------------------------------------------------------------------
apiVersion: serving.knative.dev/v1
kind: Service
metadata:
name: ruvector-benchmark
labels:
app: ruvector
component: benchmark
annotations:
run.googleapis.com/description: "RuVector GPU Benchmark Service"
run.googleapis.com/launch-stage: BETA
spec:
template:
metadata:
annotations:
# GPU Configuration
run.googleapis.com/execution-environment: gen2
run.googleapis.com/gpu-type: nvidia-l4
run.googleapis.com/gpu-count: "1"
# Scaling Configuration
autoscaling.knative.dev/minScale: "0"
autoscaling.knative.dev/maxScale: "10"
# Performance Configuration
run.googleapis.com/cpu-throttling: "false"
run.googleapis.com/startup-cpu-boost: "true"
spec:
containerConcurrency: 80
timeoutSeconds: 3600
serviceAccountName: ruvector-sa
containers:
- name: ruvector
image: gcr.io/PROJECT_ID/ruvector-benchmark:latest
ports:
- containerPort: 8080
resources:
limits:
cpu: "4"
memory: "8Gi"
nvidia.com/gpu: "1"
env:
- name: RUVECTOR_GPU_ENABLED
value: "true"
- name: RUST_LOG
value: "info"
- name: RUVECTOR_MODE
value: "benchmark"
startupProbe:
httpGet:
path: /health
port: 8080
initialDelaySeconds: 10
periodSeconds: 10
failureThreshold: 3
livenessProbe:
httpGet:
path: /health
port: 8080
periodSeconds: 30
readinessProbe:
httpGet:
path: /health
port: 8080
periodSeconds: 10
---
# -----------------------------------------------------------------------------
# Attention/GNN Service (High Memory GPU)
# -----------------------------------------------------------------------------
apiVersion: serving.knative.dev/v1
kind: Service
metadata:
name: ruvector-attention
labels:
app: ruvector
component: attention
annotations:
run.googleapis.com/description: "RuVector Attention/GNN Inference Service"
spec:
template:
metadata:
annotations:
run.googleapis.com/execution-environment: gen2
run.googleapis.com/gpu-type: nvidia-l4
run.googleapis.com/gpu-count: "1"
autoscaling.knative.dev/minScale: "1"
autoscaling.knative.dev/maxScale: "5"
run.googleapis.com/cpu-throttling: "false"
spec:
containerConcurrency: 20
timeoutSeconds: 3600
containers:
- name: ruvector
image: gcr.io/PROJECT_ID/ruvector-benchmark:latest
ports:
- containerPort: 8080
resources:
limits:
cpu: "8"
memory: "16Gi"
nvidia.com/gpu: "1"
env:
- name: RUVECTOR_MODE
value: "attention"
- name: RUVECTOR_GNN_LAYERS
value: "3"
- name: RUVECTOR_GNN_HEADS
value: "8"
- name: RUVECTOR_GNN_HIDDEN_DIM
value: "512"
- name: RUST_LOG
value: "info"
---
# -----------------------------------------------------------------------------
# Raft Consensus Node (Stateful)
# -----------------------------------------------------------------------------
apiVersion: serving.knative.dev/v1
kind: Service
metadata:
name: ruvector-raft-node-1
labels:
app: ruvector
component: raft
raft-node-id: "0"
annotations:
run.googleapis.com/description: "RuVector Raft Consensus Node"
spec:
template:
metadata:
annotations:
autoscaling.knative.dev/minScale: "1"
autoscaling.knative.dev/maxScale: "1"
run.googleapis.com/cpu-throttling: "false"
spec:
containerConcurrency: 100
timeoutSeconds: 3600
containers:
- name: ruvector
image: gcr.io/PROJECT_ID/ruvector-benchmark:latest
ports:
- containerPort: 8080
resources:
limits:
cpu: "2"
memory: "4Gi"
env:
- name: RUVECTOR_MODE
value: "raft"
- name: RUVECTOR_NODE_ID
value: "0"
- name: RUVECTOR_CLUSTER_SIZE
value: "3"
- name: RUVECTOR_RAFT_ELECTION_TIMEOUT
value: "150"
- name: RUVECTOR_RAFT_HEARTBEAT_INTERVAL
value: "50"
- name: RUST_LOG
value: "info,raft=debug"
volumeMounts:
- name: raft-data
mountPath: /data/raft
volumes:
- name: raft-data
emptyDir:
sizeLimit: "10Gi"
---
# -----------------------------------------------------------------------------
# Replication Primary Node
# -----------------------------------------------------------------------------
apiVersion: serving.knative.dev/v1
kind: Service
metadata:
name: ruvector-primary
labels:
app: ruvector
component: replication
role: primary
annotations:
run.googleapis.com/description: "RuVector Primary Node (Replication)"
spec:
template:
metadata:
annotations:
run.googleapis.com/execution-environment: gen2
run.googleapis.com/gpu-type: nvidia-l4
run.googleapis.com/gpu-count: "1"
autoscaling.knative.dev/minScale: "1"
autoscaling.knative.dev/maxScale: "1"
run.googleapis.com/cpu-throttling: "false"
spec:
containerConcurrency: 100
timeoutSeconds: 3600
containers:
- name: ruvector
image: gcr.io/PROJECT_ID/ruvector-benchmark:latest
ports:
- containerPort: 8080
resources:
limits:
cpu: "4"
memory: "8Gi"
nvidia.com/gpu: "1"
env:
- name: RUVECTOR_MODE
value: "primary"
- name: RUVECTOR_REPLICATION_FACTOR
value: "3"
- name: RUVECTOR_SYNC_MODE
value: "async"
- name: RUST_LOG
value: "info"
---
# -----------------------------------------------------------------------------
# Replication Replica Node
# -----------------------------------------------------------------------------
apiVersion: serving.knative.dev/v1
kind: Service
metadata:
name: ruvector-replica
labels:
app: ruvector
component: replication
role: replica
annotations:
run.googleapis.com/description: "RuVector Replica Node (Replication)"
spec:
template:
metadata:
annotations:
run.googleapis.com/execution-environment: gen2
run.googleapis.com/gpu-type: nvidia-l4
run.googleapis.com/gpu-count: "1"
autoscaling.knative.dev/minScale: "2"
autoscaling.knative.dev/maxScale: "5"
run.googleapis.com/cpu-throttling: "false"
spec:
containerConcurrency: 100
timeoutSeconds: 3600
containers:
- name: ruvector
image: gcr.io/PROJECT_ID/ruvector-benchmark:latest
ports:
- containerPort: 8080
resources:
limits:
cpu: "4"
memory: "8Gi"
nvidia.com/gpu: "1"
env:
- name: RUVECTOR_MODE
value: "replica"
- name: RUVECTOR_PRIMARY_URL
value: "https://ruvector-primary-HASH.run.app"
- name: RUST_LOG
value: "info"
---
# -----------------------------------------------------------------------------
# Service Account
# -----------------------------------------------------------------------------
apiVersion: iam.cnrm.cloud.google.com/v1beta1
kind: IAMServiceAccount
metadata:
name: ruvector-sa
spec:
displayName: "RuVector Cloud Run Service Account"