Related papers: Understanding the Physics of Key-Value Cache Compr…

Large language models have shown exceptional capabilities in a wide range of tasks, such as text generation and video generation, among others. However, due to their massive parameter count, these models often require substantial storage…

Efficient deployment of Large Language Models (LLMs) requires batching multiple requests together to improve throughput. As the batch size, context length, or model size increases, the size of the key and value (KV) cache can quickly become…

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…

Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources. Beyond the memory taken up by model weights, the memory…

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they…

Agentic code tasks such as fault localization and patch generation require processing long codebases under tight memory constraints, where the Key-Value (KV) cache becomes the primary inference bottleneck. Existing compression methods rely…

Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat. However,…

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the…

Inference on large language models (LLMs) can be expensive in terms of the compute and memory costs involved, especially when long sequence lengths are used. In particular, the self-attention mechanism used in LLM inference contributes…

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…

Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few…

Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typically managed through compaction in token space via summarization. However, summarization…

Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-context inference. While general KV cache compression…

Long-rollout causal video diffusion has converged on a fixed-size sliding-window KV cache, with recent progress innovating within this layout by changing which tokens occupy the window or how their positions are encoded. The per-head KV…

Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear KV cache growth. Prior approaches mitigate this via post-hoc selection or eviction but overlook the root inefficiency: indiscriminate writing to…

The growing memory footprint of the Key-Value (KV) cache poses a severe scalability bottleneck for long-context Large Language Model (LLM) inference. While KV cache eviction has emerged as an effective solution by discarding less critical…

KV cache offloading enables long-context LLM inference by storing caches in CPU DRAM, but PCIe bandwidth limitations create severe bottlenecks. In this paper, we develops an analytical framework that derives $\kappa_{\text{crit}}$, the…

The development of large language models (LLMs) has revolutionized automated code generation. However, their high demand of computation resources has hindered a broader deployment and raised environmental concerns. A common strategy for…

KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair footprint -- quantization and low-rank decomposition -- are orthogonal to those that reduce the sequence length of the cache.…

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive…