5 papers
Beaver: Elastic GPU Sharing between ML and Latency-Critical vRAN Workloads
Yuncheng Yao, Zhenzhou Qi, Junyao Zheng +3
Within the shared industry vision of AI-RAN, AI-and-RAN seeks to co-locate virtualized radio access network (vRAN) workloads and AI services on shared GPUs. This sharing is inheren…
Parallel Prefix Verification for Speculative Generation
Yuncheng Yao, Yuxuan Xia, Shengjie Wang +1
We introduce PARSE (PArallel pRefix Speculative Engine), a speculative generation framework that accelerates large language model (LLM) inference by parallelizing prefix verificati…
Foundry: Template-Based CUDA Graph Context Materialization for Fast LLM Serving Cold Start
Xueshen Liu, Yongji Wu, Yuncheng Yao +3
Modern LLM service providers increasingly rely on autoscaling and parallelism reconfiguration to respond to rapidly changing workloads, but cold-start latency remains a major bottl…
Aspen: Making Leaderless BFT Fast Paths Practical with Synchronized Clocks
Daniel Qian, Xiyu Hao, Jinkun Geng +4
No Byzantine Fault Tolerant (BFT) protocol can commit a request in less than the single round trip it takes for clients to reach the replicas and hear back. Some protocols approach…
DecodeX: Exploring and Benchmarking of LDPC Decoding across CPU, GPU, and ASIC Platforms
Zhenzhou Qi, Yuncheng Yao, Yiming Li +4
Emerging virtualized radio access networks (vRANs) demand flexible and efficient baseband processing across heterogeneous compute substrates. In this paper, we present DecodeX, a u…