Tencent releases a DSpine parallel draft model for Qwen3.8-27B

Tencent released Qwen3.8-27B-DSpine-b16 on Hugging Face for speculative decoding with Qwen3.8-27B. The model card describes a five-layer draft model with a block size of 16 and an 8,192-token sliding window. DSpine generates draft tokens in parallel, passing predicted predecessor features to adjacent positions at each layer to carry causal dependencies through network depth. The page provides a SGLang serving configuration and evaluation settings for general and agent tasks. The weights are licensed under Apache 2.0.

Written by dalao.ai: the title, summary and why it matters are our own words. The original reports are the record; their publishers keep authorship.