Related papers: Multi-Head Low-Rank Attention
Large Language Models (LLMs) with expanding context windows face significant performance hurdles. While caching key-value (KV) states is critical for avoiding redundant computation, the storage footprint of long-context caches quickly…
Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization,…
With the rapid development of large language models (LLMs), handling long context has become one of the vital abilities in LLMs. Such long-context ability is accompanied by difficulties in deployment, especially due to the increased…
Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…
Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge…
The efficiency of large language models (LLMs) remains a critical challenge, particularly in contexts where computational resources are limited. Traditional attention mechanisms in these models, while powerful, require significant…
Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the…
Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…
Attention based Transformer architecture has enabled significant advances in the field of natural language processing. In addition to new pre-training techniques, recent improvements crucially rely on working with a relatively larger…
Large language models (LLMs) show excellent performance in difficult tasks, but they often require massive memories and computational resources. How to reduce the parameter scale of LLMs has become research hotspots. In this study, we make…
The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…
KV cache is a widely used acceleration technique for large language models (LLMs) inference. However, its memory requirement grows rapidly with input length. Previous studies have reduced the size of KV cache by either removing the same…
Autoregressive large language models (LLMs) are bottlenecked by sequential decoding, where each new token typically requires executing all transformer layers. Existing dynamic-depth and layer-skipping methods reduce this cost, but often…
Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…
Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve…
Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…
Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…
The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…
Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…
Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…