draft model
1 article tagged with draft model
November 9, 2026
researchTencent
Tencent releases DSpine draft model for Qwen3.8-27B: 16-token blocks, up to 3.84× agent speedup over autoregressive deco
Tencent has published Qwen3.8-27B-DSpine-b16, a five-layer draft model with a 16-token block size and an 8,192-token sliding window, under Apache 2.0. According to its model card, it beats DFlash2 on acceptance length across five general benchmarks and on end-to-end agent throughput in SGLang.