14 citations · 29 across the 8 of their papers we have counts for
8 papers
Beyond Attention Masks: Instruction Anchoring for Efficient In-Context Diffusion Generation
Yangshuai Liu, Zheming Li, Jiaao Li +4
In-context diffusion transformers concatenate instruction, target, and reference tokens into a single sequence for joint attention. Reference-side computation must therefore be rep…
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…
TENT: A Declarative Slice Spraying Engine for Performant and Resilient Data Movement in Disaggregated LLM Serving
Feng Ren, Ruoyu Qin, Teng Ma +16
Modern GPU clusters rely on complex, heterogeneous interconnects. As large language model (LLM) serving shifts toward agentic reasoning, KVCache becomes a first-class mobile asset,…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +333
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
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…
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
Ruoyu Qin, Zheming Li, Weiran He +4
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates the prefill and de…