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.
Install
npx skills add davila7/claude-code-templates@speculative-decodingRuns in your terminal. Adds the skill globally for Claude Code, Cursor, Codex and others; add -g -y to skip prompts.
What it does
Speculative Decoding: Accelerating LLM Inference When to Use This Skill Use Speculative Decoding when you need to: - Speed up inference by 1.5-3.6× without quality loss - Reduce latency for real-time applications (chatbots, code generation) - Optimize throughput for high-volume serving - Deploy efficiently on limited hardware - Generate faster without changing model architecture Key Techniques: Draft model speculative decoding, Medusa (multiple heads), Lookahead Decoding (Jacobi iteration) Papers: Medusa (arXiv 2401.10774), Lookahead Decoding (ICML 2024), Speculative Decoding Survey (ACL…
Excerpt from the skill's own SKILL.md. Read the full file on GitHub before installing: skills run with your agent's permissions.
View source on GitHubBefore you install
Skills are plain text instructions the agent follows, sometimes with scripts. Check the source, prefer repositories with many installs and stars, and read any script it ships.
Categories
Related skills
- jira
davila7/claude-code-templates
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.
1.1K installs 31KAI & agentsProductivity - conversation-memory
davila7/claude-code-templates
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
1.0K installs 31KAI & agents - crewai-multi-agent
davila7/claude-code-templates
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
996 installs 31KAI & agents - langchain
davila7/claude-code-templates
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
976 installs 31KReact & Next.jsAI & agentsGit & GitHub - modal-serverless-gpu
davila7/claude-code-templates
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
972 installs 31KDeploy & DevOpsDataPython - context7-auto-research
davila7/claude-code-templates
Automatically fetch latest library/framework documentation for Claude Code via Context7 API
736 installs 31KReact & Next.jsDocumentationResearch