incoai releases Qwen3.8-27B-DFlash2 draft model for speculative decoding
incoai · hf · 2026-08-20
incoai released Qwen3.8-27B-DFlash2, a block-diffusion based DFlash2 draft model for speculative decoding to speed up inference. It supports SGLang and vLLM and is trending on Hugging Face.
Related event: Qwen3.8-27B DFlash2 Draft Model Speeds Up Inference via Block-Diffusion(2 posts)→
More from Models
- Opus 5.5 value may end the habit of using the top model for everything — adonis_singh · 2026-10-16
- Peter Yang: Opus 5.5 Still Struggles to Hold Its Ground When Pushed Back — petergyang · 2026-10-16
- Robot Startup Ditches VLAs for Frontier LLMs in a Customer Deployment — ihorbeaver · 2026-10-16
- Musk amplifies user claim that Grok's computer use is fast enough to skip a Codex subscription — elonmusk · 2026-10-16
- PhoneLLM launches open voice-AI models with sub-100ms latency, tops PhoneBench at 83% — charles_irl · 2026-10-16
- Transluce vets: a year of neuron autointerp work still can't explain complex behaviors — aryaman2020 · 2026-10-16