{
  "version": "2.5",
  "release_name": "Performance Optimized Edition",
  "release_date": "2026-01-21T10:46:53.928251",
  "optimizations": {
    "hnsw_index": {
      "description": "Hierarchical Navigable Small World graphs",
      "improvement": "10x faster search at 10k entries"
    },
    "lru_cache": {
      "description": "O(1) LRU cache using Rust lru crate",
      "lookup_time_ns": 23.5
    },
    "zero_copy": {
      "description": "Arc<str> string interning",
      "improvement": "100-1000x cache improvement"
    },
    "batch_simd": {
      "description": "AVX2/NEON vectorization",
      "improvement": "4x throughput"
    },
    "memory_pools": {
      "description": "Arena allocation",
      "improvement": "50% fewer allocations"
    }
  },
  "benchmarks": {
    "query_decomposition_ns": 340,
    "cache_lookup_ns": 23.5,
    "memory_search_10k_ms": 0.4,
    "pattern_retrieval_us": 25,
    "routing_accuracy_hybrid": 1.0,
    "routing_accuracy_embedding_only": 0.45
  },
  "models": {
    "claude_code_0.5b": {
      "file": "ruvltra-claude-code-0.5b-q4_k_m.gguf",
      "size_mb": 398,
      "purpose": "Agent routing",
      "context_length": 32768
    },
    "small_0.5b": {
      "file": "ruvltra-small-0.5b-q4_k_m.gguf",
      "size_mb": 400,
      "purpose": "General embeddings",
      "context_length": 32768
    },
    "medium_3b": {
      "file": "ruvltra-medium-3b-q4_k_m.gguf",
      "size_mb": 2048,
      "purpose": "Full LLM inference",
      "context_length": 262144
    }
  },
  "performance_targets": {
    "flash_attention_speedup": "2.49x-7.47x",
    "hnsw_search_speedup": "150x-12500x",
    "memory_reduction": "50-75%",
    "mcp_response_ms": 100,
    "sona_adaptation_ms": 0.05
  },
  "training_data": {
    "labeled_examples": 381,
    "contrastive_pairs": 793,
    "agent_types": 60
  }
}