5 papers
Anchoring Instruction Outside Mask: Exact Reference Caching for Efficient In-Context Diffusion Transformers
Yangshuai Liu, Zheming Li, Jiaao Li +4
Omnimodal generation is central to a wide range of content creation and editing applications. In-context conditioning is essential to this paradigm. It allows diffusion transformer…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation
Jinliang Shen, Lianghao Su, Zheming Li +4
Autoregressive (AR) video diffusion models have become a promising paradigm for long and streaming video synthesis, but the continuously growing Key-Value (KV) cache makes attentio…
Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter
Ruoyu Qin, Weiran He, Yaoyu Wang +5
Prefill-decode (PD) disaggregation has become the standard architecture for large-scale LLM serving, but in practice its deployment boundary is still determined by KVCache transfer…
Kimi K2: Open Agentic Intelligence
Kimi Team, Yifan Bai, Yiping Bao +195
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which…