← Search

Aniruddha Nrusimha

2 accepted papers

2024

Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

NeurIPS 2024poster

Key-value (KV) caching plays an essential role in accelerating decoding for transformer-based autoregressive large language models (LLMs). However, the amount of memory required to store the KV cache can become prohibitive at long sequence lengths and large batch sizes. Since the invention of the tr…

Cited by 40SourcePDFScholar
2022

Integer-Only Zero-Shot Quantization for Efficient Speech Recognition

ICASSP 2022accepted

End-to-end neural network models achieve improved performance on various automatic speech recognition (ASR) tasks. However, these models perform poorly on edge hardware due to large memory and computation requirements. While quantizing model weights and/or activations to low-precision can be a promi…

Cited by 0SourceScholar