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.
安装
npx skills add davila7/claude-code-templates --skill speculative-decodingnpx skills add davila7/claude-code-templates --skill speculative-decoding -a claude-code -gnpx skills add davila7/claude-code-templates --skill speculative-decoding -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/emerging-techniques-speculative-decodinggh skill install davila7/claude-code-templates speculative-decodinggit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/emerging-techniques-speculative-decoding ~/.claude/skills/speculative-decoding # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/emerging-techniques-speculative-decoding ~/.agents/skills/speculative-decoding # Codex, Cursor, Gemini CLI, Copilot, OpenCode