Related papers: TokenFlow: Responsive LLM Text Streaming Serving u…

Large language models (LLMs) increasingly play an important role in a wide range of information processing and management tasks in industry. Many of these tasks are performed in large batches or even offline, and the performance indicator…

Current large language model (LLM) serving systems, primarily designed for text completion, are neither efficient nor adaptable for increasingly complex LLM applications due to their inflexible design. We propose a new LLM serving system…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…

Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like…

Large Language Models (LLMs) are increasingly applied to data-intensive workflows, from database querying to developer observability. Yet the effectiveness of these systems is constrained by the volume, verbosity, and noise of real-world…

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…

Stream processing is a compute paradigm that promises safe and efficient parallelism. Modern big-data problems are often well suited for stream processing's throughput-oriented nature. Realization of efficient stream processing requires…

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…

Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This…

TensorFlow is a popular cloud computing framework that targets machine learning applications. It separates the specification of application logic (in a dataflow graph) from the execution of the logic. TensorFlow's native runtime executes…

The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on…

With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…

Serving large language models (LLMs) for massive users is challenged by the significant memory footprint of the transient state, known as the key-value (KV) cache, which scales with sequence length and number of requests. Instead of renting…

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to…

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…

Recent advances in long-text understanding have pushed the context length of large language models (LLMs) up to one million tokens. It boosts LLMs's accuracy and reasoning capacity but causes exorbitant computational costs and…

Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promises to exploit paralinguistic information in the speech and to…