5 citations · 5 across the 9 of their papers we have counts for
7 papers · 1 filter
TomasuLLM: Out-of-Order Speculative Execution for LLM Agents
Jiangnan Yu, Ceyu Xu, Mengming Li +6
Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. This observation stall presents…
Memory Compression for High-Fanout Agent Sandboxes
Mengming Li, Ceyu XU, Qijun Zhang +4
High-fanout agent workloads create a growing memory bottleneck because a single task may spawn many concurrent sandbox sessions. Yet these sandboxes are far from independent: they…
Why Do Prefetchers Fail? Let Agents Answer
Xiangfeng Sun, Ceyu Xu, Ningzhi Ai +3
Hardware prefetchers are crucial to processor performance, yet their design remains labor-intensive and expert-driven. Architects inspect execution and memory-access traces, identi…
Cache-Resident LLM Inference in GB-Scale Last-Level Caches
Wanning Zhang, Tongzhou Gu, Marco Canini +2
Large language model (LLM) inference is increasingly dominated by data movement across the memory hierarchy. Recent 3D-stacked cache technologies have enabled GB-scale last-level c…
ICP: Exploiting Instruction Correlation for Prefetching Irregular Memory Accesses
Mengming Li, Chenlu Miao, Buqing Xu +7
Irregular memory accesses pose challenges for effective and efficient data prefetching. While temporal prefetchers have recently shown promise for irregular memory access patterns,…
STS: Efficient Sparse Attention with Speculative Token Sparsity
Jiangnan Yu, Ceyu Xu, Yongji Wu +1
The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is particularly acute for emerging…
VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization
Yipu Zhang, Jintao Cheng, Xingyu Liu +8
3D reconstruction and view synthesis are fundamental to AR/VR, robotics, and digital twins. The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstru…