1 citations · 2 across the 4 of their papers we have counts for
4 papers
Phase-Decoupled, Model-Calibrated Power Control for Disaggregated LLM Serving
Jae Gon Kim, Donghoon Yoo, Hanyul Ryu +3
Datacenter GPU power is the binding constraint on LLM serving capacity, and production serving has shifted to prefill/decode (PD) disaggregation. Deploying NVIDIA's Max-Q inference…
ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
Sihwa Lee, Janghwan Lee, Donghoon Yoo +4
Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference of…
ShortcutFusion: From Tensorflow to FPGA-based accelerator with reuse-aware memory allocation for shortcut data
Duy Thanh Nguyen, Hyeonseung Je, Tuan Nghia Nguyen +3
Residual block is a very common component in recent state-of-the art CNNs such as EfficientNet or EfficientDet. Shortcut data accounts for nearly 40% of feature-maps access in ResN…
GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent
Heesu Kim, Hanmin Park, Taehyun Kim +6
In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training. As one of processing-in-memory techniqu…