Tencent opens up DSpine parallel speculative-decoding drafter
Tencent
Tencent published inference code and weights of DSpine, a ~1B parallel speculative-decoding drafter for the Qwen3-8B target model, under Apache-2.0 on Hugging Face. Its depth-conditioned network drafts all positions in parallel and reaches a 7.83 average acceptance length at T=0, ahead of DSpark, DFlash2, DFlash and Domino. The paper (arXiv 2609.36173) appeared in September 2026; the code release lands in this window.
Why it matters
Open, drop-in drafter that speeds up serving of mainstream open models like Qwen3-8B.
Importance: 2/5
notable update (minor version with real changes)