Anand Iyer
where else to find them
what they talk about
where they keep going back
no series more than once — all 6 in the filters
on a stage with
all 14 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| USHER: Holistic Interference Avoidance for Resource Optimized ML Inference | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24) | 2024-07-10 |
System claims a concrete 2.6× higher goodput and 3.5× better cost-efficiency on large-scale tests by combining a fast kernel-based estimator that predicts… | ||
| Vulcan: Automatic Query Planning for Live ML Analytics | 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) | 2024-04-16 |
Vulcan automatically generates full query plans for live ML analytics by building pipelines, deciding filter order, and jointly optimizing operator placement… | ||
| Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge | NSDI 2023 | 2023-04-17 |
Gemel is a system that jointly retrains and merges layers and weights across edge vision models so one copy of shared layers fits in GPU memory, combined with… | ||
| Production Grade Kafka on K8s | Kubernetes Community Days Chennai 2022 | 2022-06-03 |
Shows a concrete path to run production Kafka on Kubernetes using a Kafka Operator (Strimzi) that deploys brokers and ZooKeeper from a single CRD, runs an… | ||
| Preview: Graph NNs | OSDI '21 / USENIX ATC '21 | 2021-07-14 |
Overview of graph representation learning and GNNs with concrete system results: shallow encoders are transductive lookups while deep GNN encoders are… | ||
| Run your Business with Real-time Insights from Data | Google Cloud Next '18 | 2018-07-24 |
GO‑JEK moves from day‑old reports to minute‑fresh analytics by piping events through Pub/Sub, processing and windowing with Dataflow, and writing results into… | ||
| nothing matches | ||