4 citations · 10 across the 5 of their papers we have counts for
6 papers
PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis
Shengkun Cui, Rahul Krishna, Saurabh Jha +1
Unresolved production cloud incidents cost an average of over $2M per hour. This paper introduces PRAXIS, an orchestrator that manages and deploys an agentic workflow for diagnosin…
Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUs
Shengkun Cui, Archit Patke, Hung Nguyen +11
This study characterizes GPU resilience in Delta, a large-scale AI system that consists of 1,056 A100 and H100 GPUs, with over 1,300 petaflops of peak throughput. We used 2.5 years…
Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction
Haoran Qiu, Weichao Mao, Archit Patke +7
Large language models (LLMs) have been driving a new wave of interactive AI applications across numerous domains. However, efficiently serving LLM inference requests is challenging…
Watch Out for the Safety-Threatening Actors: Proactively Mitigating Safety Hazards
Saurabh Jha, Shengkun Cui, Zbigniew Kalbarczyk +1
Despite the successful demonstration of autonomous vehicles (AVs), such as self-driving cars, ensuring AV safety remains a challenging task. Although some actors influence an AV's…
ML-driven Malware that Targets AV Safety
Saurabh Jha, Shengkun Cui, Subho S. Banerjee +3
Ensuring the safety of autonomous vehicles (AVs) is critical for their mass deployment and public adoption. However, security attacks that violate safety constraints and cause acci…
Live Forensics for Distributed Storage Systems
Saurabh Jha, Shengkun Cui, Tianyin Xu +6
We present Kaleidoscope an innovative system that supports live forensics for application performance problems caused by either individual component failures or resource contention…