Related papers: FlowMM: Cross-Modal Information Flow Guided KV Cac…

Large language models (LLMs) are often used for infilling tasks, which involve predicting or generating missing information in a given text. These tasks typically require multiple interactions with similar context. To reduce the computation…

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, particularly with long…

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Key-Value (KV) cache quantization has become a widely adopted optimization technique for efficient large language models (LLMs) inference by reducing KV cache memory usage and mitigating memory-bound constraints. Recent studies have…

Large language models (LLMs) substantially enhance developer productivity in repository-level code generation through interactive collaboration. However, as interactions progress, repository context must be continuously preserved and…

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly…

Attention-based motion aggregation concepts have recently shown their usefulness in optical flow estimation, in particular when it comes to handling occluded regions. However, due to their complexity, such concepts have been mainly…

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We…

Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns…

In long-context Large Language Model (LLM) inference, the Time-To-First-Token (TTFT) latency incurred by the prefill stage has become the foremost bottleneck limiting interactive performance and deployment cost. KV Cache reuse offers a…

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…

Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challenges for efficient…

Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by…

Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models (LLMs). However, how MLLMs process and utilize visual…

Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the…

Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs. Current methods employ machine…

Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual attributes of users and items. Recent focus on the…

Large Language Models are increasingly being deployed in datacenters. Serving these models requires careful memory management, as their memory usage includes static weights, dynamic activations, and key-value caches. While static weights…

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

Large language models (LLMs) have shown great performance on complex reasoning tasks but often require generating long intermediate thoughts before reaching a final answer. During generation, LLMs rely on a key-value (KV) cache for…