Related papers: Injecting Adrenaline into LLM Serving: Boosting Re…

Multi-head latent attention (MLA) is designed to optimize KV cache memory through low-rank key-value joint compression. Rather than caching keys and values separately, MLA stores their compressed latent representations, reducing memory…

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention…

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long…

With reasoning becoming the generative paradigm for large language models (LLMs), the memory bottleneck caused by KV cache during the decoding phase has become a critical factor limiting high-concurrency service. Although existing KV cache…

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

The use of Large Language Models (LLMs) for querying relational data has given rise to relQuery, a workload pattern that applies templated LLM calls to structured tables. As relQuery services become more widely adopted in applications such…

Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel inference performance when trying to scale up the model size. To mitigate this important…

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

LLM inference must meet strict latency SLOs (e.g., 100 ms P99 time-between-tokens) while maximizing goodput. Yet, real-world variability in prompt and response lengths skews compute-intensive prefill and memory-bound decode phases, making…

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation…

Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless nature of LLMs makes managing user context (e.g., sessions, preferences) across geo-distributed edge…

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…

Large language models (LLMs) demonstrate an impressive ability to utilise information within the context of their input sequences to appropriately respond to data unseen by the LLM during its training procedure. This ability is known as…

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled powerful semantic and multimodal reasoning capabilities, creating new opportunities to enhance sample efficiency, high-level planning, and…

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding methods like Skeleton-of-Thought…

Multimodal large language models (MLLMs) extend LLMs with visual understanding through a three-stage pipeline: multimodal preprocessing, vision encoding, and LLM inference. While these stages enhance capability, they introduce significant…

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data,…