Canlyniadau Chwilio - Chen, Haibo

SMEPilot: Characterizing and Optimizing LLM Inference with Scalable Matrix Extensions gan Chen, Feiyang, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

Towards Lock Modularization for Heterogeneous Environments gan Zhang, Hanze, Chen, Rong, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents gan Wang, Yuan, Li, Mingyu, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning gan Ding, Haoran, Wang, Zhaoguo, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework gan Cao, Dong, Xu, Lisha, Chen, HaiBo

Cael y testun llawn
Cael y testun llawn

KRCORE: a microsecond-scale RDMA control plane for elastic computing gan Wei, Xingda, Lu, Fangming, Chen, Rong, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

Fast multipole boundary element method for the acoustic analysis of finite periodic structures gan Jelich, Christopher, Zhao, Wenchang, Chen, Haibo, Marburg, Steffen

Cael y testun llawn
Cael y testun llawn

TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer gan Chen, Haibo, Zhao, Lei, Li, Jun, Yang, Jian

Cael y testun llawn
Cael y testun llawn

PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU gan Song, Yixin, Mi, Zeyu, Xie, Haotong, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

ProMoE: Fast MoE-based LLM Serving using Proactive Caching gan Song, Xiaoniu, Zhong, Zihang, Chen, Rong, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption gan Tan, Yifan, Tan, Cheng, Mi, Zeyu, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

Optimizing Tree-structure Indexes for CXL-based Heterogeneous Memory with SINLK gan Zhao, Haoru, Dong, Mingkai, Wu, Fangnuo, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

FairBatching: Fairness-Aware Batch Formation for LLM Inference gan Lyu, Hongtao, Liu, Boyue, Wu, Mingyu, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

Towards Fully-fledged GPU Multitasking via Proactive Memory Scheduling gan Shen, Weihang, Chen, Yinqiu, Chen, Rong, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

Out-of-Distribution Generalization in Graph Foundation Models gan Li, Haoyang, Chen, Haibo, Wang, Xin, Zhu, Wenwu

Cael y testun llawn
Cael y testun llawn

Determinism-Preserving GPU Spatial Sharing with Vitamin-E gan Yang, Zhenyuan, Zheng, Wenxin, Li, Mingyu, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses gan Chen, Le, Feng, Erhu, Xia, Yubin, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

VUDA: Enabling Controlled Spatial Sharing of Graphics and Compute on NVIDIA GPUs gan Xu, Bin, Hu, Pengfei, Gu, Jinyu, Chen, Haibo

Cael y testun llawn
Cael y testun llawn

Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models gan Wang, Xin, Chen, Haibo, Liu, Wenxuan, Zhu, Wenwu

Cael y testun llawn
Cael y testun llawn

ParaCell: Paravirtualized Secure Containers with Lightweight Intra-Container Isolation and Intent-Driven Memory Management gan Wu, Yiyang, Wang, Xunjie, Gu, Jinyu, Chen, Haibo

Cael y testun llawn
Cael y testun llawn