Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash

Large language models (LLMs) are increasingly being deployed on mobile devices, but the limited DRAM capacity constrains the deployable model size. This paper introduces ActiveFlow, the first LLM inference framework that can achieve adaptive DRAM usage for modern LLMs (not ReLU-based), enabling the scaling up of deployable model sizes. The framework is based on the novel concept of active weight DRAM-flash swapping and incorporates three novel techniques: (1) Cross-layer active weights preloading. It uses the activations from the current layer to predict the active weights of several subsequent layers, enabling computation and data loading to overlap, as well as facilitating large I/O transfers. (2) Sparsity-aware self-distillation. It adjusts the active weights to align with the dense-model output distribution, compensating for approximations introduced by contextual sparsity. (3) Active weight DRAM-flash swapping pipeline. It orchestrates the DRAM space allocation among the hot weight cache, preloaded active weights, and computation-involved weights based on available memory. Results show ActiveFlow achieves the performance-cost Pareto frontier compared to existing efficiency optimization methods.

BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache

The growing adoption of long-context Large Language Models (LLMs) has introduced significant memory and computational challenges in autoregressive decoding due to the expanding Key-Value (KV) cache. KV cache quantization has emerged as a promising solution, with prior work showing that 4-bit or even 2-bit quantization can maintain model accuracy while reducing memory costs. However, despite these benefits, preliminary implementations for the low-bit KV cache struggle to deliver the expected speedup due to quantization and dequantization overheads and the lack of Tensor Cores utilization. In this work, we propose BitDecoding, a GPU-optimized framework that unlocks Tensor Cores for efficient decoding with low-bit KV cache. Efficiently leveraging Tensor Cores for low-bit KV cache is challenging due to the dynamic nature of KV cache generation at each decoding step. BitDecoding addresses these challenges with a Tensor Cores-Centric BitFusion Scheme that ensures data layout compatibility to enable high utilization of Tensor Cores. Additionally, BitDecoding incorporates a warp-efficient parallel decoding kernel and a fine-grained asynchronous pipeline, minimizing dequantization overhead and improving computational efficiency. Experiments show that BitDecoding achieves up to 7.5x speedup on RTX 4090, 4.8x on A100, and 8.9x on H100, compared to FP16 FlashDecoding-v2. It also outperforms the state-of-the-art low-bit KV cache implementation (QServe) by up to 4.3x. On LLaMA-3.1-8B with a 128K sequence length, BitDecoding reduces single-batch decoding latency by 3x, demonstrating its effectiveness in long-context generation scenarios. The code is available at https://github.com/DD-DuDa/BitDecoding.

Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment

We propose V-Droid, a mobile GUI task automation agent. Unlike previous mobile agents that utilize Large Language Models (LLMs) as generators to directly generate actions at each step, V-Droid employs LLMs as verifiers to evaluate candidate actions before making final decisions. To realize this novel paradigm, we introduce a comprehensive framework for constructing verifier-driven mobile agents: the discretized action space construction coupled with the prefilling-only workflow to accelerate the verification process, the pair-wise progress preference training to significantly enhance the verifier's decision-making capabilities, and the scalable human-agent joint annotation scheme to efficiently collect the necessary data at scale. V-Droid sets a new state-of-the-art task success rate across several public mobile task automation benchmarks: 59.5% on AndroidWorld, 38.3% on AndroidLab, and 49% on MobileAgentBench, surpassing existing agents by 9.5%, 2.1%, and 9%, respectively. Furthermore, V-Droid achieves an impressively low latency of 0.7 seconds per step, making it the first mobile agent capable of delivering near-real-time, effective decision-making capabilities.

StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition

With the rise of real-world human-AI interaction applications, such as AI assistants, the need for Streaming Video Dialogue is critical. To address this need, we introduce \sys, a video LLM framework that achieves ultra-FPS streaming video processing (100 fps on a single A100) and enables proactive, always-on responses in real time, without explicit user intervention. To solve the key challenge of the contradiction between linear video streaming speed and quadratic transformer computation cost, we propose a novel perception-cognition interleaving paradigm named ''event-gated LLM invocation'', in contrast to the existing per-time-step LLM invocation. By introducing a Cognition Gate network between the video encoder and the LLM, LLM is only invoked when relevant events occur. To realize the event feature extraction with constant cost, we propose Event-Preserving Feature Extractor (EPFE) based on state-space method, generating a single perception token for spatiotemporal features. These techniques enable the video LLM with full-FPS perception and real-time cognition response. Experiments on Ego4D and SoccerNet streaming tasks, as well as standard offline benchmarks, demonstrate state-of-the-art performance in both model capability and real-time efficiency, paving the way for ultra-high-FPS applications, such as Game AI Copilot and interactive media.

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs

The advent of 1-bit large language models (LLMs), led by BitNet b1.58, has spurred interest in ternary LLMs. Despite this, research and practical applications focusing on efficient edge inference for ternary LLMs remain scarce. To bridge this gap, we introduce Bitnet.cpp, an inference system optimized for BitNet b1.58 and ternary LLMs. Given that mixed-precision matrix multiplication (mpGEMM) constitutes the bulk of inference time in ternary LLMs, Bitnet.cpp incorporates a novel mpGEMM library to facilitate sub-2-bits-per-weight, efficient and lossless inference. The library features two core solutions: Ternary Lookup Table (TL), which addresses spatial inefficiencies of previous bit-wise methods, and Int2 with a Scale (I2_S), which ensures lossless edge inference, both enabling high-speed inference. Our experiments show that Bitnet.cpp achieves up to a 6.25x increase in speed over full-precision baselines and up to 2.32x over low-bit baselines, setting new benchmarks in the field. Additionally, we expand TL to element-wise lookup table (ELUT) for low-bit LLMs in the appendix, presenting both theoretical and empirical evidence of its considerable potential. Bitnet.cpp is publicly available at https://github.com/microsoft/BitNet/tree/paper , offering a sophisticated solution for the efficient and practical deployment of edge LLMs.

LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator

The emergence of neural network capabilities invariably leads to a significant surge in computational demands due to expanding model sizes and increased computational complexity. To reduce model size and lower inference costs, recent research has focused on simplifying models and designing hardware accelerators using low-bit quantization. However, due to numerical representation limits, scalar quantization cannot reduce bit width lower than 1-bit, diminishing its benefits. To break through these limitations, we introduce LUT-DLA, a Look-Up Table (LUT) Deep Learning Accelerator Framework that utilizes vector quantization to convert neural network models into LUTs, achieving extreme low-bit quantization. The LUT-DLA framework facilitates efficient and cost-effective hardware accelerator designs and supports the LUTBoost algorithm, which helps to transform various DNN models into LUT-based models via multistage training, drastically cutting both computational and hardware overhead. Additionally, through co-design space exploration, LUT-DLA assesses the impact of various model and hardware parameters to fine-tune hardware configurations for different application scenarios, optimizing performance and efficiency. Our comprehensive experiments show that LUT-DLA achieves improvements in power efficiency and area efficiency with gains of $1.4$~$7.0\times$ and $1.5$~$146.1\times$, respectively, while maintaining only a modest accuracy drop. For CNNs, accuracy decreases by $0.1\%$~$3.1\%$ using the $L_2$ distance similarity, $0.1\%$~$3.4\%$ with the $L_1$ distance similarity, and $0.1\%$~$3.8\%$ when employing the Chebyshev distance similarity. For transformer-based models, the accuracy drop ranges from $1.4\%$ to $3.0\%$.

LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuning

The escalating demand for long-context applications has intensified the necessity of extending the LLM context windows. Despite recent fine-tuning approaches successfully expanding context lengths, their high memory footprints, especially for activations, present a critical practical limitation. Current parameter-efficient fine-tuning methods prioritize reducing parameter update overhead over addressing activation memory constraints. Similarly, existing sparsity mechanisms improve computational efficiency but overlook activation memory optimization due to the phenomenon of Shadowy Activation. In this paper, we propose LeMo, the first LLM fine-tuning system that explores and exploits a new token-level sparsity mechanism inherent in long-context scenarios, termed Contextual Token Sparsity. LeMo minimizes redundant token involvement by assessing the informativeness of token embeddings while preserving model accuracy. Specifically, LeMo introduces three key techniques: (1) Token Elimination, dynamically identifying and excluding redundant tokens across varying inputs and layers. (2) Pattern Prediction, utilizing well-trained predictors to approximate token sparsity patterns with minimal overhead. (3) Kernel Optimization, employing permutation-free and segment-based strategies to boost system performance. We implement LeMo as an end-to-end fine-tuning system compatible with various LLM architectures and other optimization techniques. Comprehensive evaluations demonstrate that LeMo reduces memory consumption by up to 1.93x and achieves up to 1.36x speedups, outperforming state-of-the-art fine-tuning systems.

Ripple: Accelerating LLM Inference on Smartphones with Correlation-Aware Neuron Management

Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge due to their extensive computational and memory demands. While lightweight LLMs have been developed to fit mobile environments, they suffer from degraded model accuracy. In contrast, sparsity-based techniques minimize DRAM usage by selectively transferring only relevant neurons to DRAM while retaining the full model in external storage, such as flash. However, such approaches are critically limited by numerous I/O operations, particularly on smartphones with severe IOPS constraints. In this paper, we propose Ripple, a novel approach that accelerates LLM inference on smartphones by optimizing neuron placement in flash memory. Ripple leverages the concept of Neuron Co-Activation, where neurons frequently activated together are linked to facilitate continuous read access and optimize data transfer efficiency. Our approach incorporates a two-stage solution: an offline stage that reorganizes neuron placement based on co-activation patterns, and an online stage that employs tailored data access and caching strategies to align well with hardware characteristics. Evaluations conducted on a variety of smartphones and LLMs demonstrate that Ripple achieves up to 5.93x improvements in I/O latency compared to the state-of-the-art. As the first solution to optimize storage placement under sparsity, Ripple explores a new optimization space at the intersection of sparsity-driven algorithm and storage-level system co-design in LLM inference.

Making Every Frame Matter: Continuous Video Understanding for Large Models via Adaptive State Modeling

Video understanding has become increasingly important with the rise of multi-modality applications. Understanding continuous video poses considerable challenges due to the fast expansion of streaming video, which contains multi-scale and untrimmed events. We introduce a novel system, C-VUE, to overcome these issues through adaptive state modeling. C-VUE has three key designs. The first is a long-range history modeling technique that uses a video-aware approach to retain historical video information. The second is a spatial redundancy reduction technique, which enhances the efficiency of history modeling based on temporal relations. The third is a parallel training structure that incorporates the frame-weighted loss to understand multi-scale events in long videos. Our C-VUE offers high accuracy and efficiency. It runs at speeds >30 FPS on typical edge devices and outperforms all baselines in accuracy. Moreover, applying C-VUE to a video foundation model as a video encoder in our case study resulted in a 0.46-point enhancement (on a 5-point scale) on the in-distribution dataset, and an improvement ranging from 1.19\% to 4\% on zero-shot datasets.

SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity limits the efficiency and scalability of LLMs, especially for those with a long-context window. A promising approach addressing this limitation is to leverage the sparsity in attention. However, existing sparsity-based solutions predominantly rely on predefined patterns or heuristics to approximate sparsity. This practice falls short to fully capture the dynamic nature of attention sparsity in language-based tasks. This paper argues that attention sparsity should be learned rather than predefined. To this end, we design SeerAttention, a new Attention mechanism that augments the conventional attention with a learnable gate that adaptively selects significant blocks in an attention map and deems the rest blocks sparse. Such block-level sparsity effectively balances accuracy and speedup. To enable efficient learning of the gating network, we develop a customized FlashAttention implementation that extracts the block-level ground truth of attention map with minimum overhead. SeerAttention not only applies to post-training, but also excels in long-context fine-tuning. Our results show that at post-training stages, SeerAttention significantly outperforms state-of-the-art static or heuristic-based sparse attention methods, while also being more versatile and flexible to adapt to varying context lengths and sparsity ratios. When applied to long-context fine-tuning with YaRN, SeerAttention can achieve a remarkable 90% sparsity ratio at a 32k context length with minimal perplexity loss, offering a 5.67x speedup over FlashAttention-2.