Latency Reduction skills
Free agent skills tagged latency reduction, ready to install into any SKILL.md-compatible agent.
3 skills
Speculative Decoding
davila7
Accelerate LLM inference with advanced techniques.
Developer ToolsintermediatePython · Shell30.2k repo
Qdrant Search Optimization
github
Diagnose and fix slow Qdrant search performance.
Developer Toolsintermediate37.7k repo
Jetson Speculative Decoding
nvidia
Enhance token generation speed on Jetson vLLM servers.
Developer ToolsintermediateShell2.8k repo
Topology Optimizer
ruvnet
Optimize dynamic swarm network topologies and communication.
Developer ToolsadvancedNode · Shell67.6k repo
