Related papers: TokenDance: Scaling Multi-Agent LLM Serving via Co…

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…

We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold over sequence chunks. At each step, the model processes the next chunk conditioned on the…

In Large Language Model (LLM) serving, the KV-cache (KVC) bottleneck causes high tail Time-to-First-Token (TTFT) and Time-Between-Tokens (TBT), impairing user experience, particularly in time-sensitive applications. However, satisfying both…

Whether attention key value (KV) states computed for one prompt for a small LLM can be reused to accelerate inference on a new similar prompt, giving an increase to the space to its context memory using an approach called token recycling.…

Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their computational demands, particularly the quadratic complexity of attention mechanisms and…

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction methods reduce this cost but typically degrade performance relative to full-cache…

KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the KV cache as a lightweight representation, eliminating the…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression methods primarily…

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG)…

Large Reasoning Models (LRMs) are becoming integral to many AI inference systems, enhancing their capabilities with advanced reasoning. However, deploying these models in production environments presents a significant QoS challenge: the…

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across…

Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization…

Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major…

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…

Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains that are not attainable by a single model. In existing designs, LLMs communicate through text, forcing…

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…

Efficient KV cache management in LLMs is crucial for long-context tasks like RAG and summarization. Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics and reducing the retention of…