speculative decoding

A detailed walkthrough for running a local coding agent on macOS with llama.cpp, Gemma 4, MTP speculative decoding, image support, and Pi as the agent interface.

Google Developers Blog post about integrating DFlash, a diffusion-style speculative decoding framework, into the vLLM TPU ecosystem to improve LLM serving speed on TPU v5p.

arXiv paper on a self-speculative decoding framework for speeding up reasoning LLM inference on edge hardware, with hardware co-design and reported speedups.