mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-22 19:56:25 +00:00
4d5d3bb092
* docs: Add comprehensive GNN v2 implementation plans Add 22 detailed planning documents for 19 advanced GNN features: Tier 1 (Immediate - 3-6 months): - GNN-Guided HNSW Routing (+25% QPS) - Incremental Graph Learning/ATLAS (10-100x faster updates) - Neuro-Symbolic Query Execution (hybrid neural + logical) Tier 2 (Medium-Term - 6-12 months): - Hyperbolic Embeddings (Poincaré ball model) - Degree-Aware Adaptive Precision (2-4x memory reduction) - Continuous-Time Dynamic GNN (concept drift detection) Tier 3 (Research - 12+ months): - Graph Condensation (10-100x smaller graphs) - Native Sparse Attention (8-15x GPU speedup) - Quantum-Inspired Attention (long-range dependencies) Novel Innovations (10 experimental features): - Gravitational Embedding Fields, Causal Attention Networks - Topology-Aware Gradient Routing, Embedding Crystallization - Semantic Holography, Entangled Subspace Attention - Predictive Prefetch Attention, Morphological Attention - Adversarial Robustness Layer, Consensus Attention Includes comprehensive regression prevention strategy with: - Feature flag system for safe rollout - Performance baseline (186 tests + 6 search_v2 tests) - Automated rollback mechanisms Related to #38 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * feat(micro-hnsw-wasm): Add neuromorphic HNSW v2.3 with SNN integration ## New Crate: micro-hnsw-wasm v2.3.0 - Published to crates.io: https://crates.io/crates/micro-hnsw-wasm - 11.8KB WASM binary with 58 exported functions - Neuromorphic vector search combining HNSW + Spiking Neural Networks ### Core Features - HNSW graph-based approximate nearest neighbor search - Multi-distance metrics: L2, Cosine, Dot product - GNN extensions: typed nodes, edge weights, neighbor aggregation - Multi-core sharding: 256 cores × 32 vectors = 8K total ### Spiking Neural Network (SNN) - LIF (Leaky Integrate-and-Fire) neurons with membrane dynamics - STDP (Spike-Timing Dependent Plasticity) learning - Spike propagation through graph topology - HNSW→SNN bridge for similarity-driven neural activation ### Novel Neuromorphic Features (v2.3) - Spike-Timing Vector Encoding (rate-to-time conversion) - Homeostatic Plasticity (self-stabilizing thresholds) - Oscillatory Resonance (40Hz gamma synchronization) - Winner-Take-All Circuits (competitive selection) - Dendritic Computation (nonlinear branch integration) - Temporal Pattern Recognition (spike history matching) - Combined Neuromorphic Search pipeline ### Performance Optimizations - 5.5x faster SNN tick (2,726ns → 499ns) - 18% faster STDP learning - Pre-computed reciprocal constants - Division elimination in hot paths ### Documentation & Organization - Reorganized docs into subdirectories (gnn/, implementation/, publishing/, status/) - Added comprehensive README with badges, SEO, citations - Added benchmark.js and test_wasm.js test suites - Added DEEP_REVIEW.md with performance analysis - Added Verilog RTL for ASIC synthesis 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
277 lines
8.2 KiB
YAML
277 lines
8.2 KiB
YAML
# =============================================================================
|
|
# 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"
|