Local AI 202: Get Massive Speed-ups with Speculative Decoding

Learn about speculative decoding techniques like EAGLE, DFlash, MTP with llama.cpp, transformers and speculators library in this livestream. Links to slides and schedule: 18.10: Introduction to Speculative Decoding (Merve Noyan, Hugging Face) canva.link/zdxl8tm1xl0rcyi 18.30: Getting Started with Speculators (Eldar Kurtić, RedHat) docs.google.com/presentation/d/1VrXoh2uwI8CUZ2ZsMDlZFzkbq58i 19.00: Speed-up Gemma-4 with MTP Drafters (Maarten Grootendorst, Google DeepMind)