Related papers: CASK: Core-Aware Selective KV Compression for Reas…
We study KV cache eviction under a shared globally capped decode-time harness. Seven policies (LRU, H2O, SnapKV, StreamingLLM, Ada-KV, QUEST, Random) share a prompt-boundary vulnerability: without structural protection, they collapse to…
Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression…
Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime overhead of the transformer's Key-Value cache. To mitigate this, recent methods employ a…
As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding…
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…
While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…
Multimodal large language models suffer from substantial inference overhead since multimodal KV Cache grows proportionally with the visual input length. Existing multimodal KV Cache compression methods mostly rely on attention score to…
Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces that increase latency and memory usage. Existing LRMs typically…
The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV cache compression methods typically rely on input-side…
We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning…
Long-context inference in large language models is increasingly bottlenecked by the memory and compute cost of the KV-Cache. Low-rank factorization compresses KV projections by writing $W \approx A * B$, where A produces latent KV states…
Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbose, even for simple problems, leading to wasted context,…
The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…
Growing context lengths in transformer-based language models have made the key-value (KV) cache a critical inference bottleneck. While many KV cache pruning methods have been proposed, they have not yet been adopted in major inference…
We propose cache steering, a lightweight method for implicit steering of language models via a one-shot intervention applied directly to the key-value cache. To validate its effectiveness, we apply cache steering to induce chain-of-thought…
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…
Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…
Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the sequence extends, which seriously affects memory usage and…
As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely adopted as it stores previously generated key and value…
Scaling the input context length of a large language model (LLM) incurs a significant increase in computation cost and memory footprint to maintain the attention key-value (KV) cache. Existing KV cache compression methods suffer from…