fal AI and Fireworks have published a technical deep‑dive of their new EAGLE‑4 speculative decoding system. The blog also releases Prompt Enhancement SpecBench, a public benchmark with 400 prompts across text‑to‑image, image‑to‑image, text‑to‑video and image‑to‑video tasks. In their tests on NVIDIA B300 GPUs, the EAGLE‑4 Harness achieved 660.6 tokens per second at batch size 1 on the Fireworks benchmark, a 1.63× speed‑up over the next best method. The tree‑based verification also raised acceptance length by up to 26 % on creative prompts. The work aims to cut latency for prompt‑enhancement steps that now dominate the end‑to‑end time of fast image and video models.
Why it matters
Faster prompt expansion lets developers keep interactive response times as image and video generators become near‑real‑time.
