Folgen
Kamran Razavi
Kamran Razavi
PhD Researcher
Bestätigte E-Mail-Adresse bei tk.tu-darmstadt.de - Startseite
Titel
Zitiert von
Zitiert von
Jahr
FA2: Fast, accurate autoscaling for serving deep learning inference with SLA guarantees
K Razavi, M Luthra, B Koldehofe, M Mühlhäuser, L Wang
2022 IEEE 28th Real-Time and Embedded Technology and Applications Symposium …, 2022
132022
Operator as a service: Stateful serverless complex event processing
M Luthra, S Hennig, K Razavi, L Wang, B Koldehofe
2020 IEEE International Conference on Big Data (Big Data), 1964-1973, 2020
82020
Reconciling high accuracy, cost-efficiency, and low latency of inference serving systems
M Salmani, S Ghafouri, A Sanaee, K Razavi, M Mühlhäuser, J Doyle, ...
Proceedings of the 3rd Workshop on Machine Learning and Systems, 78-86, 2023
62023
FA2: Fast, accurate autoscaling for serving deep learning inference with SLA guarantees. In 2022 IEEE 28th Real-Time and Embedded Technology and Applications Symposium (RTAS)
K Razavi, M Luthra, B Koldehofe, M Mühlhäuser, L Wang
IEEE, 146ś159. https://doi. org/10.1109/RTAS54340, 2022
62022
Distributed DNN serving in the network data plane
K Razavi, G Karlos, V Nigade, M Mühlhäuser, L Wang
Proceedings of the 5th International Workshop on P4 in Europe, 67-70, 2022
52022
IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency
S Ghafouri, K Razavi, M Salmani, A Sanaee, T Lorido-Botran, L Wang, ...
arXiv preprint arXiv:2308.12871, 2023
12023
Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling
K Razavi, S Ghafouri, M Mühlhäuser, P Jamshidi, L Wang
arXiv preprint arXiv:2404.00704, 2024
2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–7