Ant Ling(@AntLingAGI):Today, we’re introducing the Weight Cache Daemon for SGLang. 🚀 On Ling-2.6-1T FP8, it reduced weight loading to ~0.63s, up to ~780× faster than disk loading, and cut total engine startup from 8.8 minutes to ~0.53 minutes. Here’s how it works.

Ant Ling

@AntLingAGI

MoE model series with foundation (Ling), reasoning (Ring) and any-to-any (Ming) from Ant Group’s AGI initiative, @TheInclusionAI.

加入 April 2025

5 正在關注 13.4K 粉絲

Ant Ling@AntLingAGI

2026.08.22 04:36

Today, we’re introducing the Weight Cache Daemon for SGLang. 🚀 On Ling-2.6-1T FP8, it reduced weight loading to ~0.63s, up to ~780× faster than disk loading, and cut total engine startup from 8.8 minutes to ~0.53 minutes. Here’s how it works.