5 papers · 1 filter
SAC: Disaggregated KV Cache System for Sparse Attention LLMs with CXL
Ruiyang Ma, Teng Ma, Junru Li +7
The scaling of LLMs toward long-context inference has shifted the primary serving system bottleneck from computation to memory capacity. Traditional solutions for dense attention m…
Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference
Xun Sun, Shaoyuan Chen, Pingchuan Ma +18
Mixture-of-Experts (MoE) serving relies on wide expert parallelism (EP) to aggregate the memory capacity and bandwidth of many GPUs within one inference instance. This efficiency c…
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,…
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…
A Case for Asymmetric Non-Volatile Memory Architecture
Teng Ma, Mingxing Zhang, Kang Chen +2
The byte-addressable Non-Volatile Memory (NVM) is a promising technology since it simultaneously provides DRAM-like performance, disk-like capacity, and persistency. The current NV…