Kamran Razavi

16 papers A 1C 1Journal 6Unranked 7
YearRankTypeTitle / Venue / Authors
2026 — conf
Bridging CPU and GPU Autoscaling for Cost-Efficient Inference Serving.
EuroMLSys@EuroSys
Mehran Salmani, Kamran Razavi, Peter Amthor, Boris Koldehofe
2025 — conf
IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency.
ICPE (Companion)
Saeid Ghafouri, Kamran Razavi, Mehran Salmani, Alireza Sanaee, Tania Lorido-Botran, Lin Wang, Joseph Doyle, Pooyan Jamshidi
2024 J jnl
A Tale of Two Scales: Reconciling Horizontal and Vertical Scaling for Inference Serving Systems.
CoRR
Kamran Razavi, Mehran Salmani, Max Mühlhäuser, Boris Koldehofe, Lin Wang
2024 C conf
NetNN: Neural Intrusion Detection System in Programmable Networks.
ISCC
Kamran Razavi, Shayan Davari Fard, George Karlos, Vinod Nigade, Max Mühlhäuser, Lin Wang
2024 J jnl
NetNN: Neural Intrusion Detection System in Programmable Networks.
CoRR
Kamran Razavi, Shayan Davari Fard, George Karlos, Vinod Nigade, Max Mühlhäuser, Lin Wang
2024 — —
Resource Efficient Inference Serving With SLO Guarantee.
Kamran Razavi
2024 — conf
Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling.
EuroMLSys@EuroSys
Kamran Razavi, Saeid Ghafouri, Max Mühlhäuser, Pooyan Jamshidi, Lin Wang
2024 J jnl
Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling.
CoRR
Kamran Razavi, Saeid Ghafouri, Max Mühlhäuser, Pooyan Jamshidi, Lin Wang
2024 — conf
Towards Democratic Computing.
From Multimedia Communications to the Future Internet
Max Mühlhäuser, Nikolaos Alexopoulos, Uwe Gropengießer, Kamran Razavi, Lin Wang
2023 J jnl
IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency.
CoRR
Saeid Ghafouri, Kamran Razavi, Mehran Salmani, Alireza Sanaee, Tania Lorido-Botran, Lin Wang, Joseph Doyle, Pooyan Jamshidi
2023 — conf
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems.
EuroMLSys@EuroSys
Mehran Salmani, Saeid Ghafouri, Alireza Sanaee, Kamran Razavi, Max Mühlhäuser, Joseph Doyle, Pooyan Jamshidi, Mohsen Sharifi
2023 J jnl
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems.
CoRR
Mehran Salmani, Saeid Ghafouri, Alireza Sanaee, Kamran Razavi, Max Mühlhäuser, Joseph Doyle, Pooyan Jamshidi, Mohsen Sharifi
2022 — conf
Distributed DNN serving in the network data plane.
EuroP4@CoNEXT
Kamran Razavi, George Karlos, Vinod Nigade, Max Mühlhäuser, Lin Wang
2022 A conf
FA2: Fast, Accurate Autoscaling for Serving Deep Learning Inference with SLA Guarantees.
RTAS
Kamran Razavi, Manisha Luthra, Boris Koldehofe, Max Mühlhäuser, Lin Wang
2020 — conf
Operator as a Service: Stateful Serverless Complex Event Processing.
IEEE BigData
Manisha Luthra, Sebastian Hennig, Kamran Razavi, Lin Wang, Boris Koldehofe
2020 J jnl
Operator as a Service: Stateful Serverless Complex Event Processing.
CoRR
Manisha Luthra, Sebastian Hennig, Kamran Razavi, Lin Wang, Boris Koldehofe