Related papers: Token-Budget-Aware Pool Routing for Cost-Efficient…

Deploying large language model (LLM) inference at scale requires jointly selecting base models, provisioning heterogeneous GPUs, configuring parallelism, and distributing workloads under tight latency, accuracy, and budget constraints.…

The widespread growth in LLM developments increasingly demands more computational power from clusters than what they can supply. Traditional LLM applications inherently require huge static resource allocations, which force users to either…

Reasoning LLMs produce thousands of chain-of-thought tokens whose KV cache must reside in scarce GPU HBM. The dominant response -- permanently evicting low-importance tokens -- is catastrophic for reasoning: accuracy collapses to 0-2.5%…

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Deploying transformer models in practice is challenging due to their inference cost, which scales quadratically with input sequence length. To address this, we present a novel Learned Token Pruning (LTP) method which adaptively removes…

In the context of Machine Learning as a Service (MLaaS) clouds, the extensive use of Large Language Models (LLMs) often requires efficient management of significant query loads. When providing real-time inference services, several…

Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for accelerating inference, this paper, however,…

Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the system prompt). However, the accumulated KV cache is often…

The ever-increasing computation and energy demand for LLM and AI agents call for holistic and efficient optimization of LLM serving systems. In practice, heterogeneous GPU clusters can be deployed in a geographically distributed manner,…

With the growing use of Large Language Model (LLM)-based tools like ChatGPT, Perplexity, and Gemini across industries, there is a rising need for efficient LLM inference systems. These systems handle requests with a unique two-phase…

We introduce Block-attention, an attention mechanism designed to address the increased inference latency and cost in Retrieval-Augmented Generation (RAG) scenarios. Traditional approaches often encode the entire context in an…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks…

The prohibitive training costs of Large Language Models (LLMs) have emerged as a significant bottleneck in the development of next-generation LLMs. In this paper, we show that it is possible to significantly reduce the training costs of…

The rapid growth of large language model (LLM) deployments has made cost-efficient serving systems essential. Recent efforts to enhance system cost-efficiency adopt two main perspectives: (i) An algorithmic perspective that exploits…

End-to-end Vision-Language-Action (VLA) models for autonomous driving unify perception, reasoning, and control in a single neural network, achieving strong driving performance but requiring 20-60GB of GPU memory-far exceeding the 12-16GB…

Pooling-based recurrent neural architectures consistently outperform their counterparts without pooling. However, the reasons for their enhanced performance are largely unexamined. In this work, we examine three commonly used pooling…

Transformer-based Large Language Models (LLMs) have become increasingly important. However, due to the quadratic time complexity of attention computation, scaling LLMs to longer contexts incurs extremely slow inference speed and high GPU…

The scaling law for large language models (LLMs) depicts that the path towards machine intelligence necessitates training at large scale. Thus, companies continuously build large-scale GPU clusters, and launch training jobs that span over…

The rapid adoption of Large Language Models (LLMs) has made GPU inference efficiency an increasingly critical system concern. The runtime of LLM workloads is largely dominated by tile-based kernels, particularly General Matrix…