Related papers: KV Prediction for Improved Time to First Token

Improving time-to-first-token (TTFT) is an essentially important objective in modern large language model (LLM) inference engines. Optimizing TTFT directly results in higher maximal QPS and meets the requirements of many critical…

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by…

The transformer's context window is vital for tasks such as few-shot learning and conditional generation as it preserves previous tokens for active memory. However, as the context lengths increase, the computational costs grow…

Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency resulting from the autoregressive token-by-token generation. To…

Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP) models, prompt tuning often requires a large number of…

Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-score-based KV cache pruning shows promise, it faces critical practical limitations: attention scores…

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…

Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value (KV) cache is used to store intermediate activations, which significantly lowers the computational overhead…

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Serving disaggregated large language models has been widely adopted in industrial practice for enhanced performance. However, too many tokens generated in decoding phase, i.e., occupying the resources for a long time, essentially hamper the…

Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both memory overhead and throughput bottlenecks, limiting…

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly…

Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explores an alternative axis: increasing per-token computation…

Large language models (LLMs) excel in natural language processing but demand intensive computation. To mitigate this, various quantization methods have been explored, yet they compromise LLM performance. This paper unveils a previously…

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant…

Recent large language models (LLMs) face increasing inference latency as input context length and model size continue to grow. In particular, the retrieval-augmented generation (RAG) technique, which enhances LLM responses by incorporating…

Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…

Large Language Models (LLMs) are transforming recommendation from ranking into a generative task, but industrial deployment remains limited by the high latency of processing long, personalized prompts. Standard prefix caching provides…