Chinese contentEAGLE-4 发布：无需改动模型，LLM 文字生成速度提升近 3 倍
不用改模型，装个 eagle_harness 配合 vLLM 就能让 Qwen 这类模型出字快近 3 倍，实测数据都给了，自己搭服务的可以试试。
#EAGLE-4
4 stories · 4 in 7 days · 4 in 30 days
Stories, products and papers tagged "EAGLE-4", newest first.
10月21日
EAGLE-4 Hits 863.8 Tokens/s on 27B Models
Speculative decoding delivers speedups without changing model outputs, so teams can adopt it without revalidating answer quality. Inference engineers running 27B-class models on limited hardware can treat EAGLE-4 as a drop-on layer rather than a model swap, and its measured edge over DFlash 2 and DSpark gives a concrete baseline for benchmarking their own stacks. The gains come purely from the drafting side, a direction worth watching in the decoding literature.
Chinese contentfal 与 Fireworks AI 合作提前上线 EAGLE-4
fal 联手 Fireworks AI 提前放出 EAGLE-4，主打加速创意生成工作流，技术博客里讲了原理，做生成图像的可以看看。
Chinese contentEagle Corp 开源 EAGLE-4：自适应推测解码加速 LLM 推理
做 LLM 部署的可以看看，EAGLE-4 开源了，推测解码能自适应硬件和负载，Qwen3.8-27B 实测跑到 961.6 tokens/s。
