How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

EAGLE3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark

calendar_today July 13, 2026 person Larry Li, Chao Li, Haichen Zhang, Chun Fang, Andy Luo, Spandan Tiwari, and Ashish Sirasao domain vllm

How AMD Quark trains, quantizes, and serves EAGLE3 speculative-decoding drafts with vLLM on AMD Instinct GPUs, delivering up to 2.00x throughput gains for Kimi-K2.5 and 1.79x for MiniMax-M2.5.

open_in_new Read original post