4 papers
Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference
Xun Sun, Shaoyuan Chen, Pingchuan Ma +18
Mixture-of-Experts (MoE) serving relies on wide expert parallelism (EP) to aggregate the memory capacity and bandwidth of many GPUs within one inference instance. This efficiency c…
EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration
Di Lu, Qingwen Zhang, Yujia Liu +4
Container runtimes provide a stable operational interface for deploying, monitoring, and controlling modern workloads, while trusted execution environments (TEEs) provide hardware-…
Arca: A Lightweight Confidential Container Architecture for Cloud-Native Environments
Di Lu, Mengna Sun, Qingwen Zhang +5
Confidential containers protect cloud-native workloads using trusted execution environments (TEEs). However, existing Container-in-TEE designs (e.g., Confidential Containers (CoCo)…
LightEMU: Hardware Assisted Fuzzing of Trusted Applications
Haoqi Shan, Sravani Nissankararao, Yujia Liu +4
Trusted Execution Environments (TEEs) are deployed in many CPU designs because of the confidentiality and integrity guarantees they provide. ARM TrustZone is a TEE extensively depl…