Related papers: Cross-Self KV Cache Pruning for Efficient Vision-L…
The high memory demands of the Key-Value (KV) Cache during the inference of Large Language Models (LLMs) severely restrict their deployment in resource-constrained platforms. Quantization can effectively alleviate the memory pressure caused…
With the skyrocketing costs of GPUs and their virtual instances in the cloud, there is a significant desire to use CPUs for large language model (LLM) inference. KV cache update, often implemented as allocation, copying, and in-place…
Processing long-context inputs with large language models presents a significant challenge due to the enormous memory requirements of the Key-Value (KV) cache during inference. Existing KV cache compression methods exhibit noticeable…
Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV…
Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…
Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs prohibitive inference cost. Existing pruning methods rely on…
The impressive capabilities of Large Language Models (LLMs) come at the cost of substantial computational resources during deployment. While KV Cache can significantly reduce recomputation during inference, it also introduces additional…
Large Language Models (LLMs) have shown immense potential in enhancing various aspects of our daily lives, from conversational AI to search and AI assistants. However, their growing capabilities come at the cost of extremely large model…
Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…
Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during the decoding stage, caching previous…
Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…
As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or…
Large language models (LLMs) excel at processing long sequences, boosting demand for key-value (KV) caching. While recent efforts to evict KV cache have alleviated the inference burden, they often fail to allocate resources rationally…
The computational expense of redundant vision tokens in Large Vision-Language Models (LVLMs) has led many existing methods to compress them via a vision projector. However, this compression may lose visual information that is crucial for…
This paper introduces MadaKV, a modality-adaptive key-value (KV) cache eviction strategy designed to enhance the efficiency of multimodal large language models (MLLMs) in long-context inference. In multimodal scenarios, attention heads…
Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…
Multimodal Large Language Models (MLLMs) deliver strong vision-language performance but at high computational cost, driven by numerous visual tokens processed by the Vision Transformer (ViT) encoder. Existing token pruning strategies are…
Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process…
Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…
Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…