ruvector-attention-wasm-pkg

Community

WASM attention for transformers

Authorricable
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides highly optimized WebAssembly implementations of attention mechanisms, crucial for accelerating transformer models and LLMs, especially in resource-constrained environments like web browsers or edge devices.

Core Features & Use Cases

  • High-Performance Attention: Implements MultiHead, Flash, and Hyperbolic attention with WASM for maximum speed.
  • Versatile Deployment: Runs efficiently in browsers, Node.js, and edge runtimes.
  • Use Case: Accelerate LLM token processing in a web application by offloading attention calculations to a fast, client-side WASM module.

Quick Start

Use the ruvector-attention-wasm-pkg skill to initialize the WASM module and then perform multi-head attention with the provided query, key, and value tensors.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ruvector-attention-wasm-pkg
Download link: https://github.com/ricable/cli-skills-builder/archive/main.zip#ruvector-attention-wasm-pkg

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.