AIWorksHub.io
中Publish
Back to resources

SKILL

speculative-decoding

chen-yu-haoListed
Primary machine endpointhttps://github.com/chen-yu-hao/codex-web/tree/HEAD/components/skills/ai-research/emerging-techniques-speculative-decoding
Use with an agent

SUMMARY

What it does

Accelerates LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding; optimizes speed and latency.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

machine-learningweight 100 · confidence 80gpu-computingweight 80 · confidence 80optimizationweight 80 · confidence 80

MACHINE-READABLE ENDPOINTS

How agents read it

REST JSONhttps://aiworkshub.io/api/v1/resources/RES_B62105AFAE18Canonical sourcehttps://github.com/chen-yu-hao/codex-web/blob/60f5ea7f8b4ad3b6a792f36951d957f032c8aea3/components/skills/ai-research/emerging-techniques-speculative-decoding/SKILL.md

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
60f5ea7f8b4a

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.