DeepView: A Generalizable Debugging Methodology for Enabling Large Language Models on Emerging AI Accelerators
- Kaoutar El Maghraoui
- Jordan Murray
- et al.
- 2026
- SERVICES 2026
Conference paper
Publications
49 results for Kaoutar El Maghraoui
STARC: Selective Token Access with Remapping and Clustering for Efficient LLM Decoding on PIM Systems
- Zehao Fan
- Yunzhen Liu
- et al.
- 2026
- ASPLOS 2026
Conference paperAnalog Foundation Models
- Julian Büchel
- Iason Chalas
- et al.
- 2025
- NeurIPS 2025
Conference paperAdvancing Fluorescence Light Detection and Ranging in Scattering Media with a Physics-Guided Mixture-of-Experts and Evidential Critics
- Ismail Erbas
- Ferhat Demikiran
- et al.
- 2025
- NeurIPS 2025
Workshop paperAccelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
- Yunhua Fang
- Rui Xie
- et al.
- 2025
- IEEE Computer Architecture Letters
PaperAnalog AI Accelerators for Transformer-based Language Models: Hardware, Workload, and Power Performance
- H. Tsai
- H. Benmeziane
- et al.
- 2025
- IMW 2025
Conference paperAnalog-AI Hardware Accelerators for low-latency Transformer-based Language Models (Invited)
- Geoffrey Burr
- Sidney Tsai
- et al.
- 2025
- CICC 2025
Invited talkNORA: Noise-Optimized Rescaling of LLMs on Analog Compute-in-Memory Accelerators
- Yayue Hou
- Hsinyu Tsai
- et al.
- 2025
- DATE 2025
Conference paperAIHWKIT-Lightning: A Scalable HW-Aware Training Toolkit for Analog In-Memory Computing
- Julian Büchel
- William Simon
- et al.
- 2024
- NeurIPS 2024
Workshop paperMulti-Task Neural Network Mapping onto Analog-Digital Heterogeneous Accelerators
- 2024
- NeurIPS 2024
Workshop paper