Related papers: Cocktail: Chunk-Adaptive Mixed-Precision Quantizat…

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every…

When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where output tokens are generated sequentially. Reducing the hardware cost of each decoding step is…

Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a significant challenge due to the substantial memory requirements…

Major challenges in LLMs inference remain frequent memory bandwidth bottlenecks, computational redundancy, and inefficiencies in long-sequence processing. To address these issues, we propose LLM-CoOpt, a comprehensive algorithmhardware…

As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as…

With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods…

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create…

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient low-precision decoding, it suffers from substantial…

In-context learning (ICL) capabilities are foundational to the success of large language models (LLMs). Recently, context compression has attracted growing interest since it can largely reduce reasoning complexities and computation costs of…

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by their large parameter…

Quantizing the key-value (KV) cache is a promising strategy for improving the inference efficiency of large language models (LLMs). However, aggressive quantization to very low precision (e.g., 2 bits) introduces significant errors in the…

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…

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…

The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (KV) cache, quickly overwhelming GPU memory. To address this challenge, we propose ThinKV, a…

Large language models (LLMs) with long context windows have gained significant attention. However, the KV cache, stored to avoid re-computation, becomes a bottleneck. Various dynamic sparse or TopK-based attention approximation methods have…

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…

Large Language Models (LLMs) are widely used in generative applications such as chatting, code generation, and reasoning. However, many realworld workloads such as classification, question answering, recommendation, and text embedding rely…