Dogac Eldenk

In collaboration with Fireworks and fal, we are releasing a technical analysis of EAGLE-4 alongside a public dataset for benchmarking speculative decoding on creative tasks. Why Speculative Decoding? LLMs generate text auto-regressively, predicting one token at a time. At small batch sizes, decoding relies on "thin"

At @fal , we've achieved 16 times higher throughput on Qwen3.6 for a use-case that required high interactivity per user using DSpark on SGLang. But why did we need it? And how did we achieve it? Intro Text-to-image models like Ideogram V4 can generate stunning,