Download

Skill UI

Browse and discover 10245+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search Medusa , found 1 results

Default Newest Most Downloaded

Speculative Decoding Acceleration

speculative-decoding

Orchestra-Research/AI-Research-SKILLs

Speeds up LLM inference by combining speculative decoding with Medusa multiple heads and lookahead techniques so chatbots, code assistants, and other real-time workloads can run with 1.5-3.6× lower latency while preserving target-model quality.

1

Language