From the 1 of 9 linked papers with an AI index.
9 papers
DualDecoder: Accelerate Long Context LLM Inference by Predictive Prefetch
Zuning Liang, Zhiyi Yao, Qi Chen +6
DualDecoder is a serving system that predicts and prefetches the key‑value cache entries needed for the next token in long‑context LLM inference, reducing GPU memory overhead and b…
PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention
Hong Liu, Yuan Cheng, Lin Niu +5
Token-level sparse attention, as implemented by DeepSeek Sparse Attention (DSA) in production systems, makes the downstream attention efficient but shifts the bottleneck to the ind…
Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving
Zhixin Wang, Zhengbo Wang, Fangcheng Fu +15
Heterogeneous prefill-decode (PD) inference is now in production: prefill on cost-efficient or supply-available accelerators, decode on bandwidth-strong ones, and KV state crossing…
An Efficient, Reliable and Observable Collective Communication Library in Large-scale GPU Training Clusters
Mingjun Zhang, Xiaohe Hu, Menghao Zhang +21
Large-scale LLM training requires collective communication libraries to exchange data among distributed GPUs. As a company dedicated to building and operating large-scale GPU train…
Topology-Aware Revival for Efficient Sparse Training
Meiling Jin, Fei Wang, Xiaoyun Yuan +2
Static sparse training is a promising route to efficient learning by committing to a fixed mask pattern, yet the constrained structure reduces robustness. Early pruning decisions c…
Demystifying the Slash Pattern in Attention: The Role of RoPE
Yuan Cheng, Fengzhuo Zhang, Yunlong Hou +5
Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the -th sub-diagonal for some offset . These patterns play a k…