medusa AI Agent Skills

speculative-decoding

21.8k

davila7

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

medusa

15

oimiragieo

Medusa v2 rules and best practices for modular commerce architecture, Workflow SDK, data models, services, and admin customizations.