Recent advances in context-augmented generation (CAG) techniques, particularly retrieval-augmented generation (RAG) (Gupta et al., 2024; Gao et al., 2023) and in-context learning (ICL) (Dong et al., 2022; Wei et al., 2022), have been widely adopted in large language models (LLMs) (Dubey et al., 2024; Achiam et al., 2023), improving their ability to generalize to unseen tasks with contextual information, as demonstrated in Figure 1 (top). These techniques employ a sequential encoding process to ground LLM inputs with knowledge from external sources: concatenating the retrieved texts into one sequence, and encoding the sequence into key-value (KV) states as the context for subsequent queries. While this new, significantly longer input improves performance, the increased latency in context prefilling becomes a bottleneck in tasks that require long inputs but generate short outputs (Bai et al., 2023; Agarwal et al., 2024; Jiang et al., 2024b). For example, prefilling a 128K context takes 17 seconds, whereas generating 256 tokens requires only 6 seconds. This discrepancy leaves significant room to improve the practical efficiency of CAG systems in real-world deployments (Liu, 2022; Chase, 2022).

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM applications demand flexible and high-performance attention solutions. We present FlashInfer: a customizable and efficient attention engine for LLM serving. FlashInfer tackles KV-cache storage heterogeneity using block-sparse format and composable formats to optimize memory access and reduce redundancy. It also offers a customizable attention template, enabling adaptation to various settings through Just-In-Time (JIT) compilation. Additionally, FlashInfer's load-balanced scheduling algorithm adjusts to dynamism of user requests while maintaining compatibility with CUDAGraph which requires static configuration. FlashInfer have been integrated into leading LLM serving frameworks like SGLang, vLLM and MLC-Engine. Comprehensive kernel-level and end-to-end evaluations demonstrate FlashInfer's ability to significantly boost kernel performance across diverse inference scenarios: compared to state-of-the-art LLM serving solutions, FlashInfer achieve 29-69% inter-token-latency reduction compared to compiler backends for LLM serving benchmark, 28-30% latency reduction for long-context inference, and 13-17% speedup for LLM serving with parallel generation.

Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and increasingly powerful consumer devices have made on-device deployment practical. The web browser as a platform for on-device deployment is universally accessible, provides a natural agentic environment, and conveniently abstracts out the different backends from diverse device vendors. To address this opportunity, we introduce WebLLM, an open-source JavaScript framework that enables high-performance LLM inference entirely within web browsers. WebLLM provides an OpenAI-style API for seamless integration into web applications, and leverages WebGPU for efficient local GPU acceleration and WebAssembly for performant CPU computation. With machine learning compilers MLC-LLM and Apache TVM, WebLLM leverages optimized WebGPU kernels, overcoming the absence of performant WebGPU kernel libraries. Evaluations show that WebLLM can retain up to 80% native performance on the same device, with room to further close the gap. WebLLM paves the way for universally accessible, privacy-preserving, personalized, and locally powered LLM applications in web browsers. The code is available at: https://github.com/mlc-ai/web-llm.

The applications of LLM Agents are becoming increasingly complex and diverse, leading to a high demand for structured outputs that can be parsed into code, structured function calls, and embodied agent commands. These developments bring significant demands for structured generation in LLM inference. Context-free grammar is a flexible approach to enable structured generation via constrained decoding. However, executing context-free grammar requires going through several stack states over all tokens in vocabulary during runtime, bringing non-negligible overhead for structured generation. In this paper, we propose XGrammar, a flexible and efficient structure generation engine for large language models. XGrammar accelerates context-free grammar execution by dividing the vocabulary into context-independent tokens that can be prechecked and context-dependent tokens that need to be interpreted during runtime. We further build transformations to expand the grammar context and reduce the number of context-independent tokens. Additionally, we build an efficient persistent stack to accelerate the context-dependent token checks. Finally, we co-design the grammar engine with LLM inference engine to overlap grammar computation with GPU executions. Evaluation results show that XGrammar can achieve up to 100x speedup over existing solutions. Combined with an LLM inference engine, it can generate near-zero overhead structure generation in end-to-end low-LLM serving.

We present the MIDInfinite, a web application capable of generating symbolic music using a large-scale generative AI model locally on commodity hardware. Creating this demo involved porting the Anticipatory Music Transformer, a large language model (LLM) pre-trained on the Lakh MIDI dataset, to the Machine Learning Compilation (MLC) framework. Once the model is ported, MLC facilitates inference on a variety of runtimes including C++, mobile, and the browser. We envision that MLC has the potential to bridge the gap between the landscape of increasingly capable music AI models and technology more familiar to music software developers. As a proof of concept, we build a web application that allows users to generate endless streams of multi-instrumental MIDI in the browser, either from scratch or conditioned on a prompt. On commodity hardware (an M3 Macbook Pro), our demo can generate 51 notes per second, which is faster than real-time playback for 72.9% of generations, and increases to 86.3% with 2 seconds of upfront buffering.

Deep neural networks (DNNs) continue to grow rapidly in size, making them infeasible to train on a single device. Pipeline parallelism is commonly used in existing DNN systems to support large-scale DNN training by partitioning a DNN into multiple stages, which concurrently perform DNN training for different micro-batches in a pipeline fashion. However, existing pipeline-parallel approaches only consider sequential pipeline stages and thus ignore the topology of a DNN, resulting in missed model-parallel opportunities. This paper presents graph pipeline parallelism (GPP), a new pipeline-parallel scheme that partitions a DNN into pipeline stages whose dependencies are identified by a directed acyclic graph. GPP generalizes existing sequential pipeline parallelism and preserves the inherent topology of a DNN to enable concurrent execution of computationally-independent operators, resulting in reduced memory requirement and improved GPU performance. In addition, we develop GraphPipe, a distributed system that exploits GPP strategies to enable performant and scalable DNN training. GraphPipe partitions a DNN into a graph of stages, optimizes micro-batch schedules for these stages, and parallelizes DNN training using the discovered GPP strategies. Evaluation on a variety of DNNs shows that GraphPipe outperforms existing pipeline-parallel systems such as PipeDream and Piper by up to 1.6X. GraphPipe also reduces the search time by 9-21X compared to PipeDream and Piper.

Positron Emission Tomography (PET) is an important clinical imaging tool but inevitably introduces radiation hazards to patients and healthcare providers. Reducing the tracer injection dose and eliminating the CT acquisition for attenuation correction can reduce the overall radiation dose, but often results in PET with high noise and bias. Thus, it is desirable to develop 3D methods to translate the non-attenuation-corrected low-dose PET (NAC-LDPET) into attenuation-corrected standard-dose PET (AC-SDPET). Recently, diffusion models have emerged as a new state-of-the-art deep learning method for image-to-image translation, better than traditional CNN-based methods. However, due to the high computation cost and memory burden, it is largely limited to 2D applications. To address these challenges, we developed a novel 2.5D Multi-view Averaging Diffusion Model (MADM) for 3D image-to-image translation with application on NAC-LDPET to AC-SDPET translation. Specifically, MADM employs separate diffusion models for axial, coronal, and sagittal views, whose outputs are averaged in each sampling step to ensure the 3D generation quality from multiple views. To accelerate the 3D sampling process, we also proposed a strategy to use the CNN-based 3D generation as a prior for the diffusion model. Our experimental results on human patient studies suggested that MADM can generate high-quality 3D translation images, outperforming previous CNN-based and Diffusion-based baseline methods.

Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computational costs and memory requirements. Ternarization, an extreme form of quantization, offers a solution by reducing memory usage and enabling energy-efficient floating-point additions. However, applying ternarization to LLMs faces challenges stemming from outliers in both weights and activations. In this work, observing asymmetric outliers and non-zero means in weights, we introduce Dual Learnable Ternarization (DLT), which enables both scales and shifts to be learnable. We also propose Outlier-Friendly Feature Knowledge Distillation (OFF) to recover the information lost in extremely low-bit quantization. The proposed OFF can incorporate semantic information and is insensitive to outliers. At the core of OFF is maximizing the mutual information between features in ternarized and floating-point models using cosine similarity. Extensive experiments demonstrate that our TernaryLLM surpasses previous low-bit quantization methods on the standard text generation and zero-shot benchmarks for different LLM families. Specifically, for one of the most powerful open-source models, LLaMA-3, our approach (W1.58A16) outperforms the previous state-of-the-art method (W2A16) by 5.8 in terms of perplexity on C4 and by 8.2% in terms of average accuracy on zero-shot tasks.

Deploying machine learning (ML) on diverse computing platforms is crucial to accelerate and broaden their applications. However, it presents significant software engineering challenges due to the fast evolution of models, especially the recent Large Language Models (LLMs), and the emergence of new computing platforms. Current ML frameworks are primarily engineered for CPU and CUDA platforms, leaving a big gap in enabling emerging ones like Metal, Vulkan, and WebGPU. While a traditional bottom-up development pipeline fails to close the gap timely, we introduce TapML, a top-down approach and tooling designed to streamline the deployment of ML systems on diverse platforms, optimized for developer productivity. Unlike traditional bottom-up methods, which involve extensive manual testing and debugging, TapML automates unit testing through test carving and adopts a migration-based strategy for gradually offloading model computations from mature source platforms to emerging target platforms. By leveraging realistic inputs and remote connections for gradual target offloading, TapML accelerates the validation and minimizes debugging scopes, significantly optimizing development efforts. TapML was developed and applied through a year-long, real-world effort that successfully deployed significant emerging models and platforms. Through serious deployments of 82 emerging models in 17 distinct architectures across 5 emerging platforms, we showcase the effectiveness of TapML in enhancing developer productivity while ensuring model reliability and efficiency. Furthermore, we summarize comprehensive case studies from our real-world development, offering best practices for developing emerging ML systems.

Low-dose PET offers a valuable means of minimizing radiation exposure in PET imaging. However, the prevalent practice of employing additional CT scans for generating attenuation maps (u-map) for PET attenuation correction significantly elevates radiation doses. To address this concern and further mitigate radiation exposure in low-dose PET exams, we propose POUR-Net - an innovative population-prior-aided over-under-representation network that aims for high-quality attenuation map generation from low-dose PET. First, POUR-Net incorporates an over-under-representation network (OUR-Net) to facilitate efficient feature extraction, encompassing both low-resolution abstracted and fine-detail features, for assisting deep generation on the full-resolution level. Second, complementing OUR-Net, a population prior generation machine (PPGM) utilizing a comprehensive CT-derived u-map dataset, provides additional prior information to aid OUR-Net generation. The integration of OUR-Net and PPGM within a cascade framework enables iterative refinement of $\mu$-map generation, resulting in the production of high-quality $\mu$-maps. Experimental results underscore the effectiveness of POUR-Net, showing it as a promising solution for accurate CT-free low-count PET attenuation correction, which also surpasses the performance of previous baseline methods.