EAGLE-3

NVIDIA announced that DFlash speculative decoding boosts inference performance on Blackwell GPUs by up to 15x for gpt-oss-120b and nearly doubles interactivity for Llama 3.1 8B compared to EAGLE-3. Th…

AWS invented Parallel-EAGLE (P-EAGLE), a speculative decoding method that parallelizes draft token generation, achieving up to 1.69x throughput speedup over vanilla EAGLE frameworks. Amazon SageMaker …

Researchers have developed EvoSpec, a framework that enables real-time evolution of draft models in speculative decoding through dynamic vocabulary and parameter adaptation. The system addresses the f…