15 citations · 26 across the 7 of their papers we have counts for
8 papers
Guarded Commits: Transactional Human Approvals for LLM Workflows
Laurent Bindschaedler, Ferdi Kossmann, Chunwei Liu +1
LLM workflows often require human approval before an irreversible external action. Most systems keep that approval outside the workflow, as an interface click or an audit entry. Th…
ECCO: Leveraging Cross-Camera Correlations for Efficient Live Video Continuous Learning
Yuze He, Ferdi Kossmann, Srinivasan Seshan +1
Recent advances in video analytics address real-time data drift by continuously retraining specialized, lightweight DNN models for individual cameras. However, the current practice…
KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
Eugenie Lai, Gerardo Vitagliano, Ziyu Zhang +16
Discovering insights from a real-world data lake potentially containing unclean, semi-structured, and unstructured data requires a variety of data processing tasks, ranging from ex…
Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs
Ferdi Kossmann, Bruce Fontaine, Daya Khudia +2
Serving systems for Large Language Models (LLMs) improve throughput by processing several requests concurrently. However, multiplexing hardware resources between concurrent request…
Blueprinting the Cloud: Unifying and Automatically Optimizing Cloud Data Infrastructures with BRAD -- Extended Version
Geoffrey X. Yu, Ziniu Wu, Ferdi Kossmann +5
Modern organizations manage their data with a wide variety of specialized cloud database engines (e.g., Aurora, BigQuery, etc.). However, designing and managing such infrastructure…
CascadeServe: Unlocking Model Cascades for Inference Serving
Ferdi Kossmann, Ziniu Wu, Alex Turk +3
Machine learning (ML) models are increasingly deployed to production, calling for efficient inference serving systems. Efficient inference serving is complicated by two challenges:…
Extract-Transform-Load for Video Streams
Ferdinand Kossmann, Ziniu Wu, Eugenie Lai +4
Social media, self-driving cars, and traffic cameras produce video streams at large scales and cheap cost. However, storing and querying video at such scales is prohibitively expen…
Optimizing Mixture of Experts using Dynamic Recompilations
Ferdinand Kossmann, Zhihao Jia, Alex Aiken
The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current…