← Search

Hiva Mohammadzadeh

2 accepted papers

2025

Squeezed Attention: Accelerating Long Context Length LLM Inference

ACL 2025long

Emerging Large Language Model (LLM) applications require long input context in order to perform complex tasks like document analysis and code generation.For these long context length applications, the length of the input prompt poses a significant challenge in terms of inference efficiency since the…

2024

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

NeurIPS 2024poster

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a promising approach for compressing KV cache activations; however,…