speculative-decoding
•published 2026/01/23
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.
📦 Install Skill
Command line install
Install directly with the `skills` CLI.
npx skills add davila7/claude-code-templates/cli-tool/components/skills/ai-research/emerging-techniques-speculative-decodingFile Explorer
No file selected
Select a file to view its content