Individual skill
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.
cli-tool/components/skills/ai-research/emerging-techniques-speculative-decoding/SKILL.md
Source commit ad81bf053f80b626801decf425f501ba49983d98
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 33,218
- Repository last updated
- Nov 8, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- anthropic Repository topic
- anthropic-claude Repository topic
- claude Repository topic
- claude-code Repository topic
- agent-skills Repository topic
- ai-agents Repository topic
- claude-code-plugins Repository topic
- cli Repository topic
- mcp Repository topic
- registry Repository topic
- emerging-techniques Declared skill tag
- speculative-decoding Declared skill tag
- medusa Declared skill tag
- lookahead-decoding Declared skill tag
- fast-inference Declared skill tag
- draft-models Declared skill tag
- tree-attention Declared skill tag
- parallel-generation Declared skill tag
- latency-reduction Declared skill tag
- inference-optimization Declared skill tag
- devops Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesSKILL.mdcore · 14,110 bytesreferences/lookahead.mddoc · 8,890 bytesreferences/medusa.mddoc · 9,851 bytes
Read excerpt
# 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 2024)