Best OpenVINO Models with DFlash Speculative Decoding for Intel Arc and Core Ultra
Pre-converted OpenVINO IR models and matching DFlash speculative-decoding drafts for Intel Arc GPUs and Core Ultra iGPUs, with verified hidden-state locators, stateful KV caches, and measured 2.26x–4.35x speedups.
October 19, 2026 · 6 min read