Large-language-model inference with long contexts often produces key-value (KV) caches whose footprint exceeds the capacity of high-bandwidth memory on a GPU. Prior LLM inference frameworks such as vLLM mitigate this pressure by swapping KV cache pages to host DRAM. However, the high cost of large DRAM pools makes this solution economically unattractive. Although offloading to SSDs can be a cost-effective way to expand memory capacity relative to DRAM, conventional frameworks such as FlexGen experience a substantial throughput drop since the data path that routes SSD traffic through CPU to GPU is severely bandwidth-constrained. To overcome these limitations, we introduce HiFC, a novel DRAM-free swapping scheme that enables direct access to SSD-resident memory with low latency and high effective bandwidth. HiFC stores KV pages in pseudoSLC (pSLC) regions of commodity NVMe SSDs, sustaining high throughput under sequential I/O and improving write endurance by up to 8 . Leveraging GPU Direct Storage, HiFC enables direct transfers between SSD and GPU, bypassing host DRAM and alleviating PCIe bottlenecks. HiFC employs fine-grained block mapping to confine writes to high-performance pSLC zones, stabilizing latency and throughput under load. HiFC achieves inference throughput comparable to DRAMbased swapping under diverse long-context workloads, such as NarrativeQA, while significantly lowering the memory expansion cost of a GPU server system by 4.5 over three years.

Large language models (LLMs) have shown remarkable performance across diverse reasoning and generation tasks, and are increasingly deployed as agents in dynamic environments such as code generation and recommendation systems. However, many real-world applications, such as high-frequency trading and real-time competitive gaming, require decisions under strict latency constraints, where faster responses directly translate into higher rewards. Despite the importance of this latency-quality trade-off, it remains underexplored in the context of LLM-based agents. In this work, we present the first systematic study of this trade-off in realtime decision-making tasks. To support our investigation, we introduce two new benchmarks: HFTBench, a high-frequency trading simulation, and StreetFighter, a competitive gaming platform.

Mixture-of-Experts (MoE) architecture offers enhanced efficiency for Large Language Models (LLMs) with modularized computation, yet its inherent sparsity poses significant hardware deployment challenges, including memory locality issues, communication overhead, and inefficient computing resource utilization. Inspired by the modular organization of the human brain, we propose Mozart, a novel algorithm-hardware co-design framework tailored for efficient training of MoE-based LLMs on 3.5D wafer-scale chiplet architectures. On the algorithm side, Mozartexploits the inherent modularity of chiplets and introduces: (1) an expert allocation strategy that enables efficient on-package all-to-all communication, and (2) a fine-grained scheduling mechanism that improves communication-computation overlap through streaming tokens and experts. On the architecture side, Mozart adaptively co-locates heterogeneous modules on specialized chiplets with a 2.5D NoP-Tree topology and hierarchical memory structure. Evaluation across three popular MoE models demonstrates significant efficiency gains, enabling more effective parallelization and resource utilization for large-scale modularized MoE-LLMs.

LLM-based agent applications have shown increasingly remarkable capabilities in complex workflows but incur substantial costs and latency due to extensive planning and reasoning requirements. Existing LLM caching techniques (like context caching and semantic caching), primarily designed for serving chatbots, are insufficient for agent applications where outputs depend on external data and environmental contexts. We propose Agentic Plan Caching (APC), a novel testtime memory that extracts, stores, adapts, and reuses structured plan templates from planning stages of agent applications across semantically similar tasks to reduce the cost and latency of serving. Unlike traditional semantic caching, our system extracts plan templates from completed agent executions at test-time, employs keyword extraction to match new requests against cached plans, and utilizes lightweight models to adapt these templates to task-specific plans with contexts. Evaluation across multiple real-world agent applications shows that our system can reduce costs by 50.31% and latency by 27.28% on average while maintaining performance, offering a more efficient solution for serving LLM-based agents that complements existing LLM serving infrastructures.

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components--combined with complex inference pipelines and heterogeneous workloads--introduce significant inference overhead. Therefore, efficiently serving MLLMs remains a major challenge. Current tightly coupled serving architectures struggle to distinguish between mixed request types or adapt parallelism strategies to different inference stages, leading to increased time-to-first-token (TTFT) and poor resource utilization. To address this, we introduce Elastic Multimodal Parallelism (EMP), a new serving paradigm that elastically adapts to resource heterogeneity across request types and inference stages. Building upon EMP, we develop ElasticMM, an MLLM serving system that (1) separates requests into independent modality groups with dynamic resource allocation via a modality-aware load balancer; (2) decouples inference stages and enables parallelism adjustment and adaptive scaling via elastic partition scheduling; and (3) improves inference efficiency through unified multimodal prefix caching and non-blocking encoding. Experiments on diverse real-world datasets show that ElasticMM outperforms state-of-the-art (SOTA) serving systems, reducing TTFT by up to 4.2 and achieving 3.2-4.5 higher throughput while meeting service-level objectives (SLOs).

Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edgeassisted inference framework that splits LLM workloads between edge and server GPUs using a speculative decoding scheme, exchanging only token outputs over the network. SpecEdge employs proactive edge drafting to overlap edge token creation with server verification and pipeline-aware scheduling that interleaves multiple user requests to increase server-side throughput. Experiments show SpecEdge enhances overall cost efficiency by 1.91 through achieving 2.22 server throughput, and reduces inter token latency by 11.24% compared to a server-only baseline, introducing a scalable, cost-effective paradigm for LLM serving.

Photorealistic Codec Avatars (PCA), which generate high-fidelity human face renderings, are increasingly being used in Virtual Reality (VR) environments to enable immersive communication and interaction through deep learning-based generative models. However, these models impose significant computational demands, making real-time inference challenging on resource-constrained VR devices such as head-mounted displays (HMDs), where latency and power efficiency are critical. To address this challenge, we propose an efficient post-training quantization (PTQ) method tailored for Codec Avatar models, enabling low-precision execution without compromising output quality. In addition, we design a custom hardware accelerator that can be integrated into the system-on-chip (SoC) of VR devices to further enhance processing efficiency. Building on these components, we introduce ESCA, a full-stack optimization framework that accelerates PCA inference on edge VR platforms. Experimental results demonstrate that ESCA boosts FovVideoVDP quality scores by up to +0.39 over the best 4-bit baseline, delivers up to 3.36 latency reduction, and sustains a rendering rate of 100 frames per second in endto-end tests, satisfying real-time VR requirements. These results demonstrate the feasibility of deploying high-fidelity codec avatars on resource-constrained devices, opening the door to more immersive and portable VR experiences. Paper website can be found at https://zmzfpc.github.io/ESCA/.

Accelerating large language model (LLM) inference is critical for real-world deployments requiring high throughput and low latency. Contextual sparsity, where each token dynamically activates only a small subset of the model parameters, shows promise but does not scale to large batch sizes due to union of active neurons quickly approaching dense computation. We introduce Polar Sparsity, highlighting a key shift in sparsity importance from MLP to Attention layers as we scale batch size and sequence length. While MLP layers become more compute-efficient under batching, their sparsity vanishes. In contrast, attention becomes increasingly more expensive at scale, while their head sparsity remains stable and batch-invariant. We develop Selective Head Attention with hardware-efficient, sparsity-aware GPU kernels, delivering up to 2.2 end-to-end speedups for models like OPT, LLaMA2 & 3, Qwen, Mistral across various batch sizes and sequence lengths without compromising accuracy. To our knowledge, this is the first work to demonstrate that contextual sparsity can scale effectively to large batch sizes, delivering substantial inference acceleration with minimal changes, making Polar Sparsity practical for large-scale, high-throughput LLM deployment systems.

Recent multimodal large language models (MLLMs) marry modality-specific vision or audio encoders with a shared text decoder. While the encoder is computeintensive but memory-light, the decoder is the opposite, yet state-of-the-art serving stacks still time-multiplex these complementary kernels, idling SMs or HBM in turn. We introduce SpaceServe, a serving system that space-multiplexes MLLMs: it decouples all modality encoders from the decoder, and co-locates them on the same GPU using fine-grained SM partitioning available in modern runtimes. A cost-model-guided Space-Inference Scheduler (SIS) dynamically assigns SM slices, while a Time-Windowed Shortest-Remaining-First (TWSRFT) policy batches encoder requests to minimise completion latency and smooth decoder arrivals. Evaluation shows that SpaceServe reduces time-per-output-token by 4.81 on average and up to 28.9 on Nvidia A100 GPUs.

Extremely memory-efficient model architectures are decisive to fit within an MCU's tiny memory budget e.g., 128kB of RAM. However, inference latency must remain small to fit real-time constraints. An approach to tackle this is patchbased fusion, which aims to optimize data flows across neural network layers. In this paper, we introduce msf-CNN, a novel technique that efficiently finds optimal fusion settings for convolutional neural networks (CNNs) by walking through the fusion solution space represented as a directed acyclic graph. Compared to previous work on CNN fusion for MCUs, msf-CNN identifies a wider set of solutions. We published an implementation of msf-CNN running on various microcontrollers (ARM Cortex-M, RISC-V, ESP32). We show that msf-CNN can achieve inference using 50% less RAM compared to the prior art (MCUNetV2 and StreamNet). We thus demonstrate how msf-CNN offers additional flexibility for system designers.