2 papers
cs.DC2026
fabric-lib: RDMA Point-to-Point Communication for LLM Systems
Nandor Licker, Kevin Hu, Vladimir Zaytsev +1
Emerging Large Language Model (LLM) system patterns, such as disaggregated inference, Mixture-of-Experts (MoE) routing, and asynchronous reinforcement fine-tuning, require flexible…
cs.DC2025
FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving
Zihao Ye, Lequn Chen, Ruihang Lai +8
Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for hi…