Related papers: Multi-Head Low-Rank Attention

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In these scenarios, the Key-Value (KV) cache is the primary…

Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…

Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query…

Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterogeneous structure of vision language model (VLM) inputs. We introduce \emph{Image-LoRA}, a…

Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the speculative step increases. Existing work attributes this decay to train-inference mismatch…

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require…

Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context length, resulting in a severe scalability bottleneck. Existing approaches largely treat KV…

The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…

Large language models (LLMs) enable long-context tasks but face efficiency challenges due to the growing key-value (KV) cache. We propose LeanK, a learning-based method that prunes unimportant key (K) cache channels by leveraging static…

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Large Language Model-based generative recommendation (LLMRec) has achieved notable success, but it suffers from high inference latency due to massive computational overhead and memory pressure of KV Cache. Existing KV Cache reduction…

Large language models (LLMs) have demonstrated remarkable performance on long-context tasks, but are often bottlenecked by memory constraints. Namely, the KV cache, which is used to significantly speed up attention computations, grows…

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

Long-context LLMs have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challenges, optimizations for long-context inference have been…

Multiple heads decoding accelerates the inference of Large Language Models (LLMs) by predicting next several tokens simultaneously. It generates and verifies multiple candidate sequences in parallel via tree attention with a fixed…

Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still remain bottlenecked by memory-bound attention in long-context…

Parameter-efficient fine-tuning (PEFT) has emerged as a powerful paradigm for adapting large-scale pre-trained models to downstream tasks with minimal additional parameters. Among PEFT methods, Low-Rank Adaptation (LoRA) stands out for its…

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…