Related papers: Linear Predictability of Attention Heads in Large …
As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…
Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…
In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architectures. In particular, most existing work only theoretically…
Transformers with linear recurrent modeling offer linear-time training and constant-memory inference. Despite their demonstrated efficiency and performance, pretraining such non-standard architectures from scratch remains costly and risky.…
Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of…
Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remains an open challenge. Although Chain-of-Thought prompting has…
The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either…
Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory…
The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate…
To enhance the efficiency of the attention mechanism within large language models (LLMs), previous works primarily compress the KV cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive…
The current large language models are mainly based on decode-only structure transformers, which have great in-context learning (ICL) capabilities. It is generally believed that the important foundation of its ICL capability is the induction…
Vision-language models (VLMs) show remarkable performance in multimodal tasks. However, excessively long multimodal inputs lead to oversized Key-Value (KV) caches, resulting in significant memory consumption and I/O bottlenecks. Previous KV…
A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the queried region should imply a confident, calibrated answer. We test this…
Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strategy to alleviate…
The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…
Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…
Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation…
Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice between low-latency heuristics that sacrifice precision and…
Large Language Models (LLMs) have revolutionized a wide range of domains such as natural language processing, computer vision, and multi-modal tasks due to their ability to comprehend context and perform logical reasoning. However, the…
The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…