{
  "name": "ruvector-attention-wasm",
  "type": "module",
  "version": "0.1.32",
  "description": "High-performance WebAssembly attention mechanisms for transformers and LLMs: Multi-Head, Flash Attention, Hyperbolic, Linear (Performer), MoE, Local-Global, and CGT Sheaf Attention with coherence gating. GPU-accelerated with SIMD fallback.",
  "license": "MIT OR Apache-2.0",
  "author": "RuVector Team <team@ruvector.dev>",
  "repository": {
    "type": "git",
    "url": "git+https://github.com/ruvnet/ruvector.git"
  },
  "homepage": "https://ruv.io/ruvector",
  "bugs": {
    "url": "https://github.com/ruvnet/ruvector/issues"
  },
  "main": "ruvector_attention_wasm.js",
  "module": "ruvector_attention_wasm.js",
  "types": "ruvector_attention_wasm.d.ts",
  "files": [
    "ruvector_attention_wasm_bg.wasm",
    "ruvector_attention_wasm.js",
    "ruvector_attention_wasm.d.ts",
    "ruvector_attention_wasm_bg.wasm.d.ts",
    "README.md"
  ],
  "sideEffects": [
    "./snippets/*"
  ],
  "keywords": [
    "wasm",
    "webassembly",
    "attention",
    "transformer",
    "llm",
    "machine-learning",
    "neural-networks",
    "multi-head-attention",
    "flash-attention",
    "hyperbolic",
    "moe",
    "mixture-of-experts",
    "coherence",
    "cgt",
    "sheaf-attention",
    "ai",
    "deep-learning",
    "gpu",
    "simd",
    "infonce",
    "contrastive-learning",
    "performer",
    "linear-attention"
  ],
  "engines": {
    "node": ">=16.0.0"
  },
  "publishConfig": {
    "access": "public"
  }
}