Agent Skills: emerging-techniques-speculative-decoding

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.

ID: davila7/claude-code-templates/emerging-techniques-speculative-decoding

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill emerging-techniques-speculative-decoding

Skill Files

The files that make up emerging-techniques-speculative-decoding.

Download Skill

More agent skills