4 citations · 6 across the 21 of their papers we have counts for
22 papers
Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents
Jianchang Su, Yiwei Yang, Wei Zhang
Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the model's confidence and its…
HBFSim: Fast and Faithful Simulation of High-Bandwidth Flash Under Real GPU Execution
Yanpeng Hu, Yiwei Yang, Yuanwu Zhu +3
High-Bandwidth Flash (HBF) places high-capacity NAND beside HBM to relieve the memory-capacity bottleneck of LLM inference, yet its system-level behavior cannot be evaluated before…
The Fabric Is the Cluster Driver: Cross-Layer eBPF Policies for GPU-CXL Fabrics
Yiwei Yang, Andi Quinn
We present fabric_ext, an eBPF middleware compiler and runtime for extensible OS policies over GPU--CXL fabrics. fabric_ext lets one policy program execute across GPU hooks, driver…
Concordia: JIT-Compiled Persistent-Kernel Checkpointing for Fault-Tolerant LLM Inference
Yuhang Gan, Yiwei Yang, Yuyi Li +6
Long-running LLM agents keep valuable state resident on GPUs: KV caches, request schedulers, communication state, and sometimes online adapters. Losing this state after a GPU or co…
GPUOS: A GPU Operating System Primitive for Transparent Operation Fusion
Yiwei Yang, Xiangyu Gao, Yuan Zhou +3
Modern deep learning workloads often consist of many small tensor operations, especially in inference, attention, and micro-batched training. In these settings, kernel launch overh…
DAXFS: A Lock-Free Shared Filesystem for CXL Disaggregated Memory
Cong Wang, Yiwei Yang, Yusheng Zheng
CXL (Compute Express Link) enables multiple hosts to share byte-addressable memory with hardware cache coherence, but no existing filesystem exploits this for lock-free multi-host…
ReFlux: Reversible Compute Placement for CXL-Enabled Storage
Yanpeng Hu, Yiwei Yang, Yusheng Zheng +4
Static offload to computational storage devices proves brittle because device-side processors throttle under sustained thermal load, while opaque, vendor-specific interfaces inflat…
ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
Yusheng Zheng, Yiwei Yang, Wei Zhang +1
LLM agent frameworks increasingly offer checkpoint-restore for error recovery and exploration, advising developers to make external tool calls safe to retry. This advice assumes th…
AgentCgroup: Understanding and Controlling OS Resources of AI Agents
Yusheng Zheng, Jiakun Fan, Quanzhi Fu +3
AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands…
SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning
Jianchang Su, Yifan Zhang, Shengkai Lin +4
Multi-stage ML inference pipelines are difficult to autoscale due to heterogeneous resources, cross-stage coupling, and dynamic bottleneck migration. We present SAIR, an autoscalin…
gpu_ext: Extensible OS Policies for GPUs via eBPF
Yusheng Zheng, Tong Yu, Yiwei Yang +8
Performance in modern GPU-centric systems increasingly depends on resource management policies, including memory placement, scheduling, and observability. However, uniform policies…
Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference
Kexin Chu, Dawei Xiang, Zixu Shen +3
Mixture-of-Experts (MoE) has become a practical architecture for scaling LLM capacity while keeping per-token compute modest, but deploying MoE models on a single, memory-limited G…
CXLAimPod: CXL Memory is all you need in AI era
Yiwei Yang, Yusheng Zheng, Yiqi Chen +5
The proliferation of data-intensive applications, ranging from large language models to key-value stores, increasingly stresses memory systems with mixed read-write access patterns…
Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
Kexin Chu, Zecheng Lin, Dawei Xiang +7
Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversari…
HetGPU: The pursuit of making binary compatibility towards GPUs
Yiwei Yang, Yusheng Zheng, Tong Yu +1
Heterogeneous GPU infrastructures present a binary compatibility challenge: code compiled for one vendor's GPU will not run on another due to divergent instruction sets, execution…
Exploiting Control-flow Enforcement Technology for Sound and Precise Static Binary Disassembly
Brian Zhao, Yiwei Yang, Yusheng Zheng +1
Rewriting x86_64 binaries-whether for security hardening, dynamic instrumentation, or performance profiling is notoriously difficult due to variable-length instructions, interleave…
MVVM: Deploy Your AI Agents-Securely, Efficiently, Everywhere
Yiwei Yang, Aibo Hu, Yusheng Zheng +6
The rise of AI agents powered by Large Language Models (LLMs) presents critical challenges: how to securely execute and migrate these agents across heterogeneous environments while…
Code-Survey: An LLM-Driven Methodology for Analyzing Large-Scale Codebases
Yusheng Zheng, Yiwei Yang, Haoqin Tu +1
Modern software systems like the Linux kernel are among the world's largest and most intricate codebases, continually evolving with new features and increasing complexity. Understa…
Wasm-bpf: Streamlining eBPF Deployment in Cloud Environments with WebAssembly
Yusheng Zheng, Tong Yu, Yiwei Yang +1
The extended Berkeley Packet Filter (eBPF) is extensively utilized for observability and performance analysis in cloud-native environments. However, deploying eBPF programs across…
KEN: Kernel Extensions using Natural Language
Yusheng Zheng, Yiwei Yang, Maolin Chen +1
The ability to modify and extend an operating system is an important feature for improving a system's security, reliability, and performance. The extended Berkeley Packet Filters (…
bpftime: userspace eBPF Runtime for Uprobe, Syscall and Kernel-User Interactions
Yusheng Zheng, Tong Yu, Yiwei Yang +3
In kernel-centric operations, the uprobe component of eBPF frequently encounters performance bottlenecks, largely attributed to the overheads borne by context switches. Transitioni…
CXLMemUring: A Hardware Software Co-design Paradigm for Asynchronous and Flexible Parallel CXL Memory Pool Access
Yiwei Yang, Yusheng Zheng, Kexin Chu +3
CXL-attached memory lets servers add more memory while keeping the standard load/store programming model. The main drawback is latency. CXL memory accesses are too slow for normal…