Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding

Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtime assumptions. We present Yggdrasil, a co-designed system that enables latency-optimal speculative decoding through context-aware tree drafting and compiler-friendly execution. Yggdrasil introduces an equal-growth tree structure for static graph compatibility, a latency-aware optimization objective for draft selection, and stage-based scheduling to reduce overhead. Yggdrasil supports unmodified LLMs and achieves up to $3.98\times$ speedup over state-of-the-art baselines across multiple hardware setups.

Harli: SLO-Aware Co-location of LLM Inference and PEFT-based Finetuning on Model-as-a-Service Platforms

Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of inference. However, decode instances often experience low GPU utilization due to their memory-bound nature and insufficient batching in dynamic workloads, leaving compute resources underutilized. We introduce Harli, a serving system that improves GPU utilization by co-locating parameter-efficient finetuning (PEFT) tasks with LLM decode instances. PEFT tasks are compute-bound and memory-efficient, making them ideal candidates for safe co-location. Specifically, Harli addresses key challenges--limited memory and unpredictable interference--using three components: a unified memory allocator for runtime memory reuse, a two-stage latency predictor for decode latency modeling, and a QoS-guaranteed throughput-maximizing scheduler for throughput maximization. Experimental results show that Harli improves the finetune throughput by 46.2% on average (up to 92.0%) over state-of-the-art serving systems, while maintaining strict QoS guarantees for inference decode.

MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts

The immense memory requirements of state-of-the-art Mixture-of-Experts (MoE) models present a significant challenge for inference, often exceeding the capacity of a single accelerator. While offloading experts to host memory is a common solution, it introduces a severe I/O bottleneck over the PCIe bus, as the data-dependent nature of expert selection places these synchronous transfers directly on the critical path of execution, crippling performance. This paper argues that the I/O bottleneck can be overcome by trading a small amount of cheap, on-device computation to hide the immense cost of data movement. We present MoE-SpeQ, a new inference system built on a novel co-design of speculative execution and expert offloading. MoE-SpeQ employs a small, on-device draft model to predict the sequence of required experts for future tokens. This foresight enables a runtime orchestrator to prefetch these experts from host memory, effectively overlapping the expensive I/O with useful computation and hiding the latency from the critical path. To maximize performance, an adaptive governor, guided by an Amortization Roofline Model, dynamically tunes the speculation strategy to the underlying hardware. Our evaluation on memory-constrained devices shows that for the Phi-MoE model, MoE-SpeQ achieves at most 2.34x speedup over the state-of-the-art offloading framework. Our work establishes a new, principled approach for managing data-dependent memory access in resource-limited environments, making MoE inference more accessible on commodity hardware.

Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution

Embodied AI systems operate in dynamic environments, requiring seamless integration of perception and generation modules to process high-frequency input and output demands. Traditional sequential computation patterns, while effective in ensuring accuracy, face significant limitations in achieving the necessary "thinking" frequency for real-world applications. In this work, we present Auras, an algorithm-system co-designed inference framework to optimize the inference frequency of embodied AI agents. Auras disaggregates the perception and generation and provides controlled pipeline parallelism for them to achieve high and stable throughput. Faced with the data staleness problem that appears when the parallelism is increased, Auras establishes a public context for perception and generation to share, thereby promising the accuracy of embodied agents. Experimental results show that Auras improves throughput by 2.54x on average while achieving 102.7% of the original accuracy, demonstrating its efficacy in overcoming the constraints of sequential computation and providing high throughput.

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive

Large language model (LLM) decoding suffers from high latency due to fragmented execution across operators and heavy reliance on off-chip memory for data exchange and reduction. This execution model limits opportunities for fusion and incurs significant memory traffic and kernel launch overhead. While modern architectures such as NVIDIA Hopper provide distributed shared memory and low-latency intra-cluster interconnects, they expose only low-level data movement instructions, lacking structured abstractions for collective on-chip communication. To bridge this software-hardware gap, we introduce two cluster-level communication primitives, ClusterReduce and ClusterGather, which abstract common communication patterns and enable structured, high-speed data exchange and reduction between thread blocks within a cluster, allowing intermediate results to be on-chip without involving off-chip memory. Building on these abstractions, we design ClusterFusion, an execution framework that schedules communication and computation jointly to expand operator fusion scope by composing decoding stages such as QKV Projection, Attention, and Output Projection into a single fused kernels. Evaluations on H100 GPUs show that ClusterFusion outperforms state-of-the-art inference frameworks by 1.61x on average in end-to-end latency across different models and configurations. The source code is available at https://github.com/xinhao-luo/ClusterFusion.

Adacc: Adaptive Compression and Activation Checkpointing for LLM Memory Management

Training large language models often employs recomputation to alleviate memory pressure, which can introduce up to 30% overhead in real-world scenarios. In this paper, we propose Adacc, a novel memory management framework that combines adaptive compression and activation checkpointing to reduce the GPU memory footprint. It comprises three modules: (1) We design layer-specific compression algorithms that account for outliers in LLM tensors, instead of directly quantizing floats from FP16 to INT4, to ensure model accuracy. (2) We propose an optimal scheduling policy that employs MILP to determine the best memory optimization for each tensor. (3) To accommodate changes in training tensors, we introduce an adaptive policy evolution mechanism that adjusts the policy during training to enhance throughput. Experimental results show that Adacc can accelerate the LLM training by 1.01x to 1.37x compared to state-of-the-art frameworks, while maintaining comparable model accuracy to the Baseline.

Efficient Serving of LLM Applications with Probabilistic Demand Modeling

Applications based on Large Language Models (LLMs) contains a series of tasks to address real-world problems with boosted capability, which have dynamic demand volumes on diverse backends. Existing serving systems treat the resource demands of LLM applications as a blackbox, compromising end-to-end efficiency due to improper queuing order and backend warm up latency. We find that the resource demands of LLM applications can be modeled in a general and accurate manner with Probabilistic Demand Graph (PDGraph). We then propose Hermes, which leverages PDGraph for efficient serving of LLM applications. Confronting probabilistic demand description, Hermes applies the Gittins policy to determine the scheduling order that can minimize the average application completion time. It also uses the PDGraph model to help prewarm cold backends at proper moments. Experiments with diverse LLM applications confirm that Hermes can effectively improve the application serving efficiency, reducing the average completion time by over 70% and the P95 completion time by over 80%.

Efficient Unified Caching for Accelerating Heterogeneous AI Workloads

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access. To avoid code-intrusion complexity and minimize cache space wastage, it is desirable to maintain a unified cache shared by all the workloads. However, existing cache management strategies, designed for specific workloads, struggle to handle the heterogeneous AI workloads in a cluster -- which usually exhibit heterogeneous access patterns and item storage granularities. In this paper, we propose IGTCache, a unified, high-efficacy cache for modern AI clusters. IGTCache leverages a hierarchical access abstraction, AccessStreamTree, to organize the recent data accesses in a tree structure, facilitating access pattern detection at various granularities. Using this abstraction, IGTCache applies hypothesis testing to categorize data access patterns as sequential, random, or skewed. Based on these detected access patterns and granularities, IGTCache tailors optimal cache management strategies including prefetching, eviction, and space allocation accordingly. Experimental results show that IGTCache increases the cache hit ratio by 55.6% over state-of-the-art caching frameworks, reducing the overall job completion time by 52.2%.

STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support

3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices, achieving only 2 to 9 FPS.Existing accelerators focus on compute efficiency but overlook memory efficiency, leading to redundant DRAM traffic. We introduce STREAMINGGS, a fully streaming 3DGS algorithm-architecture co-design that achieves fine-grained pipelining and reduces DRAM traffic by transforming from a tile-centric rendering to a memory-centric rendering. Results show that our design achieves up to 45.7 $\times$ speedup and 62.9 $\times$ energy savings over mobile Ampere GPUs.

Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers

Video diffusion transformers (vDiTs) have made impressive progress in text-to-video generation, but their high computational demands present major challenges for practical deployment. While existing acceleration methods reduce workload at various granularities, they often rely on heuristics, limiting their applicability. We introduce ASTRAEA, an automatic framework that searches for near-optimal configurations for vDiT-based video generation. At its core, ASTRAEA proposes a lightweight token selection mechanism and a memory-efficient, GPU-parallel sparse attention strategy, enabling linear reductions in execution time with minimal impact on generation quality. To determine optimal token reduction for different timesteps, we further design a search framework that leverages a classic evolutionary algorithm to automatically determine the distribution of the token budget effectively. Together, ASTRAEA achieves up to 2.4x inference speedup on a single GPU with great scalability (up to 13.2x speedup on 8 GPUs) while retaining better video quality compared to the state-of-the-art methods (<0.5% loss on the VBench score compared to the baseline vDiT models).