ReplaySSM：重新思考混合模型解码的状态存储以加速推理
ReplaySSM: Rethinking State Storage for Faster Hybrid-Model Decoding
NVIDIA 提出 ReplaySSM，针对 NVIDIA Nemotron 3、Qwen3.5 至 Qwen3.8、Kimi-K3、GLM-5.3-Flash 等混合模型，重新设计 SSM 层的状态存储方式以加速解码。
Hybrid models interleave state-space model (SSM) layers with a few attention layers. NVIDIA Nemotron 3, Qwen3.5 through Qwen3.8, Kimi-K3, and GLM-5.3-Flash are...
Hybrid models interleave state-space model (SSM) layers with a few attention layers. NVIDIA Nemotron 3, Qwen3.5 through Qwen3.8, Kimi-K3, and GLM-5.3-Flash are all built this way, with Mamba-2, Gated DeltaNet (GDN), or Kimi Delta Attention (KDA) as the SSM layer. SSM layers are designed to make decoding fast: they use a fixed-size state in place of a key-value (KV) cache that grows with…
来源：NVIDIA Developer Blog · developer.nvidia.com