Large-language-model inference with long contexts often produces key-value (KV) caches whose footprint exceeds the capacity of high-bandwidth memory on a GPU. Prior LLM inference frameworks such as vLLM mitigate this pressure by swapping KV cache pages to host DRAM. However, the high cost of large DRAM pools makes this solution economically unattractive. Although offloading to SSDs can be a cost-effective way to expand memory capacity relative to DRAM, conventional frameworks such as FlexGen experience a substantial throughput drop since the data path that routes SSD traffic through CPU to GPU is severely bandwidth-constrained. To overcome these limitations, we introduce HiFC, a novel DRAM-free swapping scheme that enables direct access to SSD-resident memory with low latency and high effective bandwidth. HiFC stores KV pages in pseudoSLC (pSLC) regions of commodity NVMe SSDs, sustaining high throughput under sequential I/O and improving write endurance by up to 8 . Leveraging GPU Direct Storage, HiFC enables direct transfers between SSD and GPU, bypassing host DRAM and alleviating PCIe bottlenecks. HiFC employs fine-grained block mapping to confine writes to high-performance pSLC zones, stabilizing latency and throughput under load. HiFC achieves inference throughput comparable to DRAMbased swapping under diverse long-context workloads, such as NarrativeQA, while significantly lowering the memory expansion cost of a GPU server system by 4.5 over three years.

Recent reasoning-focused language models achieve high accuracy by generating lengthy intermediate reasoning paths before producing final answers. While this approach is effective in solving problems that require logical thinking, long reasoning paths significantly increase memory usage and reduce throughput of token generation, limiting the practical deployment of such models. We propose Reasoning Path Compression (RPC), a training-free method that accelerates inference by leveraging the semantic sparsity of reasoning paths. RPC periodically compresses the KV cache by retaining cache entries that receive high importance score, which are computed using a selector window composed of recently generated queries. Experiments show that RPC improves generation throughput of QwQ-32B by up to 1.60 compared to the inference with full KV cache, with an accuracy drop of 1.2% on the AIME 2024 benchmark. Our findings demonstrate that semantic sparsity in reasoning traces can be effectively exploited for compression, offering a practical path toward efficient deployment of reasoning LLMs.

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to efficient long-context processing show promise, recurrent compression-based methods struggle with information preservation, whereas random access approaches require substantial memory resources. We introduce REFORM, a novel inference framework that efficiently handles long contexts through a two-phase approach. First, it incrementally processes input chunks while maintaining a compressed KV cache, constructs cross-layer context embeddings, and utilizes early exit strategy for improved efficiency. Second, it identifies and gathers essential tokens via similarity matching and selectively recomputes the KV cache. Compared to baselines, REFORM achieves over 52% and 34% performance gains on RULER and BABILong respectively at 1M context length. It also outperforms baselines on -Bench, RepoEval, and MM-NIAH, demonstrating flexibility across diverse tasks and domains. Additionally, REFORM reduces inference time by 30% and peak memory usage by 5%, achieving both efficiency and superior performance.

Private large language model (LLM) inference based on secure multi-party computation (MPC) achieves formal data privacy protection but suffers from significant latency overhead, especially for long input sequences. While key-value (KV) cache eviction and sparse attention algorithms have been proposed for efficient LLM inference in plaintext, they are not designed for MPC and cannot benefit private LLM inference directly. In this paper, we propose an accurate and MPC-friendly KV cache eviction framework, dubbed MPCACHE, building on the observation that historical tokens in a long sequence may have different effects on the downstream decoding. Hence, MPCACHE combines a look-once static eviction algorithm to discard unimportant KV cache and a query-aware dynamic selection algorithm to activate only a small subset of KV cache for attention computation. MPCACHE further incorporates a series of optimizations for efficient dynamic KV cache selection, including MPC-friendly similarity approximation, hierarchical KV cache clustering, and cross-layer index-sharing strategy. Extensive experiments demonstrate that MPCACHE consistently outperforms prior-art KV cache eviction baselines across different generation tasks and achieves 1.8 2.01 and 3.39 8.37 decoding latency and communication reduction on different sequence lengths, respectively. The code can be found here.

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 strategies and find per-token magnitude-based pruning as highly effective for both Key and Value caches under unstructured sparsity, surpassing prior structured pruning schemes. The Key cache benefits from prominent outlier elements, while the Value cache surprisingly benefits from a simple magnitude-based pruning despite its uniform distribution. KV cache size is the major bottleneck in decode performance due to high memory overhead for large context lengths. To address this, we use a bitmap-based sparse format and a custom attention kernel capable of compressing and directly computing over compressed caches pruned to arbitrary sparsity patterns, significantly accelerating memory-bound operations in decode computations and thereby compensating for the overhead of runtime pruning and compression. Our custom attention kernel coupled with the bitmap-based format delivers substantial compression of KV cache up to 45% of dense inference and thereby enables longer context lengths and increased tokens/sec throughput of up to 2.23 compared to dense inference.

Transformer-based Large Language Models (LLMs) have become increasingly important.

Low-Rank Adaptation (LoRA) has emerged as a highly efficient framework for finetuning the weights of large foundation models, and has become the go-to method for data-driven customization of LLMs. Despite the promise of highly customized behaviors and capabilities, switching between relevant LoRAs in a multiturn setting is inefficient, as the key-value (KV) cache of the entire turn history must be recomputed with the LoRA weights before generation can begin. To address this problem, we propose Activated LoRA (aLoRA), an adapter architecture which modifies the LoRA framework to only adapt weights for the tokens in the sequence after the aLoRA is invoked. This change crucially allows aLoRA to accept the base model's KV cache of the input string, meaning that aLoRA can be instantly activated whenever needed in a chain without recomputing the prior keys and values. This enables building what we call intrinsics, i.e. specialized models invoked to perform well-defined operations on portions of an input chain or conversation that otherwise uses the base model by default. We train a set of aLoRA-based intrinsics models, demonstrating competitive accuracy with standard LoRA while significantly improving inference efficiency. We contributed our Activated LoRA implementation to the Huggingface PEFT library.1

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible eviction strategy fails to adapt to dynamic attention patterns during decoding (the saliency shift problem), and (2) they treat both marginally important tokens and truly unimportant tokens equally, despite the collective significance of marginal tokens to model performance (the marginal information over-compression problem). To address these issues, we design two compensation mechanisms based on the high similarity of attention matrices between LLMs of different scales. We propose SmallKV, a small model assisted compensation method for KV cache compression. SmallKV can maintain attention matching between different-scale LLMs to: 1) assist the larger model in perceiving globally important information of attention; and 2) use the smaller model's attention scores to approximate those of marginal tokens in the larger model. Extensive experiments on benchmarks including GSM8K, BBH, MT-Bench, and LongBench demonstrate the effectiveness of SmallKV. Moreover, efficiency evaluations show that SmallKV achieves 1.75 2.56 times higher throughput than baseline methods, highlighting its potential for efficient and performant LLM inference in resource constrained environments.

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than the number of generated tokens. Hence, we explore inference-time hyper-scaling: by compressing the KV cache, we can generate more tokens within the same compute budget and further improve the accuracy of scaled inference. The success of this approach, however, hinges on the ability of compression methods to preserve accuracy even at high compression ratios. To make hyper-scaling practical, we introduce Dynamic Memory Sparsification (DMS), a novel method for sparsifying KV caches that only requires 1K training steps to achieve 8 compression, while maintaining better accuracy than training-free sparse attention.

We demonstrate that geometrically distinctive keys during LLM inference tend to have high attention scores. Based on the phenomenon we propose KEYDIFF, a training-free KV cache eviction method based solely on key similarity. Unlike other KV cache eviction methods, KEYDIFF can process arbitrarily long prompts within strict resource constraints and efficiently generate responses. We provide a theoretical basis for KEYDIFF by relating key diversity with attention scores. These results imply KEYDIFF can efficiently identify the most important tokens to retain. Notably KEYDIFF does not rely on attention scores, allowing the use of optimized attention mechanisms like FlashAttention. Under a strict memory allowance, we demonstrate the effectiveness of KEYDIFF for the Llama and Qwen model families by observing a performance gap of less than 0.04% with 8K cache budget ( 23% KV cache reduction) from the non-evicting baseline on LongBench for Llama 3.1-8B and Llama 3.2-3B. We also observe near baseline performance for Deepseek-R1-Distill-Llama-8B on the Math500 reasoning benchmark and decrease end-to-end inference latency by up to 30% compared to the other token-eviction methods.