speculative-decoding

SKILLWorkflowcommunity
v0.0.0Orchestra-ResearchMITUpdated 2mo agoSource →

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, Jac

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
12kRepo stars
1Clients
1Formats
2mo agoLast update
Skill
AuthorOrchestra-Research
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptOpen (see Prompt tab)
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

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.

Keywords
skillclaude