Publications

200 results for Hybrid Cloud Platform

vllm-triton-backend: How to get state-of-the-art performance on NVIDIA and AMD with just triton
- - Burkhard Ringlein
  - Thomas Parnell
  - et al.
- 2025
- PyTorch Conference 2025
Talk
The Anatomy of a Triton Attention Backend
- - Burkhard Ringlein
  - Jan van Lunteren
  - et al.
- 2025
- Triton Developer Conference 2025
Poster
Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments
- - Nikoleta Iliakopoulou
  - Jovan Stojkovic
  - et al.
- 2025
- MICRO 2025
Conference paper
Does Linux Provide Performance Isolation for NVMe SSDs? Configuring cgroups for I/O Control in the NVMe Era
- - Krijn Doekemeijer
  - Zebin Ren
  - et al.
- 2025
- IISWC 2025
Conference paper
A Framework For The Iterative Solution of Sparse Linear Systems on Hybrid Architectures Using Homomorphic Encryption
- - Lior Horesh
  - Vassilis Kalantzis
  - et al.
- 2025
- HPEC 2025
Conference paper
Networking for Stateful LLM Inference
- - Junchen Jiang
  - Yuhan Liu
  - et al.
- 2025
- SIGCOMM 2025
Tutorial
Taming the Wild West of Research Computing: How Policies Saved Us a Thousand Headaches
- - Alessandro Pomponio
- 2025
- Cloud Native Dublin 2025
Talk
Page Migration for Hardware Memory Disaggregation Across a Network
- - Archit Patke
  - Christian Pinto
  - et al.
- 2025
- ICS 2025
Conference paper
SSD controller architecture for similarity search in Vector DBs
- - Roman Pletka
  - Jovan Blanusa
  - et al.
- 2025
- FMS 2025
Conference paper
An Extensible Software Transport Layer for GPU Networking
- - Yang Zhou
  - Zhongjie Chen
  - et al.
- 2025
- arXiv
Paper