← Search

Keisuke Kamahori

2 accepted papers

2025

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

ICLR 2025poster

Large Language Models (LLMs) with the Mixture-of-Experts (MoE) architectures have shown promising performance on various tasks. However, due to the huge model sizes, running them in resource-constrained environments where the GPU memory is not abundant is challenging. Some existing systems propose t…

2025

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

EMNLP 2025

Modern automatic speech recognition (ASR) models, such as OpenAI’s Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce LiteASR, a low-rank compression scheme for ASR encoders that