相关论文: NoMAD-Attention: Efficient LLM Inference on CPUs T…

Processing long contexts has become a critical capability for modern large language models (LLMs). However, serving long-context LLMs comes with significant inference costs due to the high memory overhead of the key-value (KV) cache.…

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

PagedAttention is a popular approach for dynamic memory allocation in LLM serving systems. It enables on-demand allocation of GPU memory to mitigate KV cache fragmentation -- a phenomenon that crippled the batch size (and consequently…

Accelerating large language model (LLM) inference is critical for real-world deployments requiring high throughput and low latency. Contextual sparsity, where each token dynamically activates only a small subset of the model parameters,…

As Large Language Models (LLMs) scale to longer context windows, the computational cost of attention mechanisms, which traditionally grows quadratically with input length, presents a critical challenge for real-time and memory-constrained…

Large Audio-Language Models (LALMs) often suffer from audio-textual attention imbalance, prioritizing text over acoustic information, particularly in the multi-modal fusion layers of the Transformer architecture. This bias hinders their…

Scaling pre-trained language models has resulted in large performance gains in various natural language processing tasks but comes with a large cost in memory requirements. Inspired by the position embeddings in transformers, we aim to…

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost $O(n^2)$ in the input sequence length $n$ is a notorious obstacle for further…

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottleneck that limits their scalability. Alman and Song (NeurIPS…

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

To index the increasing volume of data, modern data indexes are typically stored on SSDs and cached in DRAM. However, searching such an index has resulted in significant I/O traffic due to limited access locality and inefficient cache…

Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations…

The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU…

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…

The rapid development of large language models (LLM) has greatly enhanced everyday applications. While many FPGA-based accelerators, with flexibility for fine-grained data control, exhibit superior speed and energy efficiency compared to…

Recent work has shown that attention-based language models excel at recall, the ability to ground generations in tokens previously seen in context. However, the efficiency of attention-based models is bottle-necked during inference by the…

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length generalization and attention's quadratic computational…