LodeHQ
AI news for people who shipFree, by email

AI · huggingface.co · Thursday, 12 November 2026

DSpine pushes Qwen3.8 decoding to 3.84× autoregressive speed

Qwen3.8 users can now run a five-layer DSpine draft model that reaches up to 3.84× the throughput of ordinary autoregressive decoding in the listed benchmarks. It predicts draft tokens in parallel, then carries each position’s causal information through later layers, using 16-token blocks and an 8,192-token sliding window. On WorkBuddy Office, it reaches 805.53 tokens per second versus 210.03 for autoregressive decoding.

Read the source: huggingface.co ↗In the 12 November issue →