Cacheon

Decentralized LLM inference optimization competition platform

Giới thiệu về Cacheon

Được thành lập2026
Cacheon is a decentralized LLM inference optimization competition platform. Miners compete for the fastest and correct Qwen2.5-72B model service speed by submitting containerized inference servers. Verifiers will conduct benchmark tests, and the fastest and correct server can obtain most of the TAO rewards.
Cộng đồng
Twitter
Website
GitHub
Ghi chú
AI

Xu hướng thay đổi chỉ số phổ biến