Tencent Technical Engineering
Jan 13, 2026 · Artificial Intelligence
Boost LLM Inference 1.9× with AngelSlim’s Speculative Decoding (Eagle3)
AngelSlim introduces a system‑wide speculative decoding framework called Eagle3 that combines lightweight draft models with parallel verification by large models, delivering up to 1.9× faster inference across LLM, vision‑language, and speech tasks while remaining open‑source and deployment‑ready.
AngelSlimEagle3LLM Acceleration
0 likes · 9 min read