arXiv subjects

Guohao Dai

Publications and source records attributed to Guohao Dai.

At least 37 records · Page 2Linked to original sources

arXiv2025

Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design

LLM-based search agents achieve strong performance but suffer from severe latency, as each step requires serialized LLM reasoning followed by action of tool execution. We revisit this bottleneck through the lens of speculation. While traditional predict-verify speculation paradigm can break serial execution, its benefit remains limited, as it retains the full original workload and adds extra inference overhead. We observe that early agent steps often involve simple evidence-gathering, where correct actions can often be predicted without full reasoning. Building on these observations, we present SPAgent, an algorithm-system co-design framework that expands the role of speculation in search agents to reduce latency. Algorithmically, SPAgent introduces a two-phase adaptive speculation mechanism that selectively omits verification when safe. System-wise, a two-level scheduler regulates speculative requests based on engine load to ensure speculation remains beneficial. We implement SPAgent in real-world systems. Across extensive experimental settings, SPAgent achieves up to $1.65\times$ end-to-end speedup while maintaining same or even achieving higher accuracy, enabling practical deployment of multi-step search agents.

cs.AI↗

arXiv2025

STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training with Spatio-Temporal Planning

The rapid scaling of large language models (LLMs) has significantly increased GPU memory pressure, which is further aggravated by training optimization techniques such as virtual pipeline and recomputation that disrupt tensor lifespans and introduce considerable memory fragmentation. Such fragmentation stems from the use of online GPU memory allocators in popular deep learning frameworks like PyTorch, which disregard tensor lifespans. As a result, this inefficiency can waste as much as 43% of memory and trigger out-of-memory errors, undermining the effectiveness of optimization methods. To address this, we introduce STAlloc, a GPU memory allocator for deep learning frameworks that reduces fragmentation by exploiting the spatial and temporal regularity in memory allocation behaviors of training workloads. STAlloc introduces a novel paradigm that combines offline planning with online allocation. The offline planning leverages spatio-temporal regularities to generate a near-optimal allocation plan, while the online allocation handles complex and dynamic models such as Mixture-of-Experts (MoE). Built as a pluggable PyTorch memory allocator, STAlloc reduces fragmentation ratio on average by 85.1% (up to 100%) across both dense and MoE models, with negligible overhead. This enables more efficient, high-throughput training configurations and improves throughput performance by up to 32.5%.

cs.LG↗

arXiv2025

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods typically employ a single window length across all attention heads and input sizes. However, this uniform approach fails to capture the heterogeneous attention patterns inherent in LLMs, ignoring their distinct accuracy-latency trade-offs. To address this challenge, we propose *Mixture of Attention Spans* (MoA), which automatically tailors distinct sliding-window length configurations to different heads and layers. MoA constructs and navigates a search space of various window lengths and their scaling rules relative to input sizes. It profiles the model, evaluates potential configurations, and pinpoints the optimal length configurations for each head. MoA adapts to varying input sizes, revealing that some attention heads expand their focus to accommodate longer inputs, while other heads consistently concentrate on fixed-length local contexts. Experiments show that MoA increases the effective context length by 3.9x with the same average sliding-window length, boosting retrieval accuracy by 1.5-7.1x over the uniform-window baseline across Vicuna-{7B, 13B} and Llama3-{8B, 70B} models. Moreover, MoA narrows the performance gap with full attention, reducing the maximum relative performance drop from 9%-36% to within 5% across three long-context understanding benchmarks. MoA achieves a 1.2-1.4x GPU memory reduction, boosting decode throughput by 6.6-8.2x and 1.7-1.9x over FlashAttention2 and vLLM, with minimal performance impact. Our code is available at: https://github.com/thu-nics/MoA

cs.LG↗

arXiv2025

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation

Feature caching has recently emerged as a promising method for diffusion model acceleration. It effectively alleviates the inefficiency problem caused by high computational requirements by caching similar features in the inference process of the diffusion model. In this paper, we analyze existing feature caching methods from the perspective of information utilization, and point out that relying solely on historical information will lead to constrained accuracy and speed performance. And we propose a novel paradigm that introduces future information via self-speculation based on the information similarity at the same time step across different iteration times. Based on this paradigm, we present \textit{SpecDiff}, a training-free multi-level feature caching strategy including a cached feature selection algorithm and a multi-level feature classification algorithm. (1) Feature selection algorithm based on self-speculative information. \textit{SpecDiff} determines a dynamic importance score for each token based on self-speculative information and historical information, and performs cached feature selection through the importance score. (2) Multi-level feature classification algorithm based on feature importance scores. \textit{SpecDiff} classifies tokens by leveraging the differences in feature importance scores and introduces a multi-level feature calculation strategy. Extensive experiments show that \textit{SpecDiff} achieves average 2.80 \times, 2.74 \times , and 3.17\times speedup with negligible quality loss in Stable Diffusion 3, 3.5, and FLUX compared to RFlow on NVIDIA A800-80GB GPU. By merging speculative and historical information, \textit{SpecDiff} overcomes the speedup-accuracy trade-off bottleneck, pushing the Pareto frontier of speedup and accuracy in the efficient diffusion model inference.

cs.CV↗

arXiv2025

BitSnap: Checkpoint Sparsification and Quantization in LLM Training

As large language models (LLMs) continue to grow in size and complexity, efficient checkpoint saving\&loading has become crucial for managing storage, memory usage, and fault tolerance in LLM training. The current works do not comprehensively take into account the optimization of these several aspects. This paper proposes a novel checkpoint sparsification and quantization method that adapts dynamically to different training stages and model architectures. We present a comprehensive analysis of existing lossy and lossless compression techniques, identify current limitations, and introduce our adaptive approach that balances compression ratio, speed, and precision impact throughout the training process. Experiments on different sizes of LLMs demonstrate that our bitmask-based sparsification method achieves 16x compression ratio without compromising model accuracy. Additionally, the cluster-based quantization method achieves 2x compression ratio with little precision loss.

cs.LG↗

arXiv2025

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled Small Language Models (SLMs) significantly enhance efficiency, their performance suffers as they fail to follow LLMs' reasoning paths. Luckily, we reveal that only a small fraction of tokens genuinely diverge reasoning paths between LLMs and SLMs. Most generated tokens are either identical or exhibit neutral differences, such as minor variations in abbreviations or expressions. Leveraging this insight, we introduce **Roads to Rome (R2R)**, a neural token routing method that selectively utilizes LLMs only for these critical, path-divergent tokens, while leaving the majority of token generation to the SLM. We also develop an automatic data generation pipeline that identifies divergent tokens and generates token-level routing labels to train the lightweight router. We apply R2R to combine R1-1.5B and R1-32B models from the DeepSeek family, and evaluate on challenging math, coding, and QA benchmarks. With an average activated parameter size of 5.6B, R2R surpasses the average accuracy of R1-7B by 1.6x, outperforming even the R1-14B model. Compared to R1-32B, it delivers a 2.8x wall-clock speedup with comparable performance, advancing the Pareto frontier of test-time scaling efficiency. Our code is available at https://github.com/thu-nics/R2R.

cs.CL↗

arXiv2025

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

Image Auto-regressive (AR) models have emerged as a powerful paradigm of visual generative models. Despite their promising performance, they suffer from slow generation speed due to the large number of sampling steps required. Although Distilled Decoding 1 (DD1) was recently proposed to enable few-step sampling for image AR models, it still incurs significant performance degradation in the one-step setting, and relies on a pre-defined mapping that limits its flexibility. In this work, we propose a new method, Distilled Decoding 2 (DD2), to further advances the feasibility of one-step sampling for image AR models. Unlike DD1, DD2 does not without rely on a pre-defined mapping. We view the original AR model as a teacher model which provides the ground truth conditional score in the latent embedding space at each token position. Based on this, we propose a novel \emph{conditional score distillation loss} to train a one-step generator. Specifically, we train a separate network to predict the conditional score of the generated distribution and apply score distillation at every token position conditioned on previous tokens. Experimental results show that DD2 enables one-step sampling for image AR models with an minimal FID increase from 3.40 to 5.43 on ImageNet-256. Compared to the strongest baseline DD1, DD2 reduces the gap between the one-step sampling and original AR model by 67%, with up to 12.3$\times$ training speed-up simultaneously. DD2 takes a significant step toward the goal of one-step AR generation, opening up new possibilities for fast and high-quality AR modeling. Code is available at https://github.com/imagination-research/Distilled-Decoding-2.

cs.LG↗

arXiv2025

LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K

State-of-the-art large language models (LLMs) are now claiming remarkable supported context lengths of 256k or even more. In contrast, the average context lengths of mainstream benchmarks are insufficient (5k-21k), and they suffer from potential knowledge leakage and inaccurate metrics, resulting in biased evaluation. This paper introduces LV-Eval, a challenging long-context benchmark with five length levels (16k, 32k, 64k, 128k, and 256k) reaching up to 256k words. LV-Eval features two main tasks, single-hop QA and multi-hop QA, comprising 11 bilingual datasets. The design of LV-Eval has incorporated three key techniques, namely confusing facts insertion, keyword and phrase replacement, and keyword-recall-based metric design. The advantages of LV-Eval include controllable evaluation across different context lengths, challenging test instances with confusing facts, mitigated knowledge leakage, and more objective evaluations. We evaluate 15 LLMs on LV-Eval and conduct ablation studies on the benchmarking techniques. The results reveal that: (i) Moonshot-v1 and recent large-scale open-source models, such as Qwen-2.5-72B and Llama-3.1-70B, achieve the highest performance on LV-Eval, particularly at lengths below 64k. (ii) Models exhibit distinct score trends. For example, GLM-4-9B-128k, Yi-6B-200k, and Llama3-8B-1M exhibit a relatively gentle degradation of performance, but their absolute performances may not necessarily be higher than those of LLMs with shorter context lengths. (iii) LLMs' performances can significantly degrade in the presence of confusing information, especially in the pressure test of "needle in a haystack". (iv) Issues related to knowledge leakage and inaccurate metrics introduce bias in evaluation, and these concerns are alleviated in LV-Eval. All datasets and evaluation codes are released at: https://github.com/infinigence/LVEval.

cs.CL↗

arXiv2025

ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts

Mixture-of-Experts (MoE) architectures have emerged as a promising approach to scale Large Language Models (LLMs). MoE boosts the efficiency by activating a subset of experts per token. Recent works show that fine-grained experts substantially enriches the combinatorial flexibility of active experts and enhances model expressiveness. However, such a design is fundamentally limited by the layer-local routing mechanism: each layer is restricted to its own expert pool. This requires a careful trade-off between expert dimensionality and routing diversity given fixed parameter budgets. We describe ReXMoE, a novel MoE architecture that improves routing beyond the existing layer-local approaches by allowing routers to reuse experts across adjacent layers. ReXMoE decouples expert dimensionality from per-layer budgets, enabling richer expert combinations without sacrificing individual expert capacity or inflating overall parameters. To this end, we propose a new progressive scaling routing (PSR) strategy to gradually increase the candidate expert pool during training. As a result, ReXMoE improves both language modeling and downstream task performance. Extensive experiments on models ranging from 0.5B to 7B parameters across different architectures demonstrate that ReXMoE consistently improves performance under fixed architectural dimensions, confirming ReXMoE as new design paradigm for parameter-efficient and scalable MoE-based LLMs.

cs.CL↗

arXiv2025

BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU

3D Gaussian Splatting (3DGS) has emerged as a promising 3D reconstruction technique. The traditional 3DGS training pipeline follows three sequential steps: Gaussian densification, Gaussian projection, and color splatting. Despite its promising reconstruction quality, this conventional approach suffers from three critical inefficiencies: (1) Skewed density allocation during Gaussian densification, (2) Imbalanced computation workload during Gaussian projection and (3) Fragmented memory access during color splatting. To tackle the above challenges, we introduce BalanceGS, the algorithm-system co-design for efficient training in 3DGS. (1) At the algorithm level, we propose heuristic workload-sensitive Gaussian density control to automatically balance point distributions - removing 80% redundant Gaussians in dense regions while filling gaps in sparse areas. (2) At the system level, we propose Similarity-based Gaussian sampling and merging, which replaces the static one-to-one thread-pixel mapping with adaptive workload distribution - threads now dynamically process variable numbers of Gaussians based on local cluster density. (3) At the mapping level, we propose reordering-based memory access mapping strategy that restructures RGB storage and enables batch loading in shared memory. Extensive experiments demonstrate that compared with 3DGS, our approach achieves a 1.44$\times$ training speedup on a NVIDIA A100 GPU with negligible quality degradation.

cs.CV↗

arXiv2025

TASP: Topology-aware Sequence Parallelism

Long-context large language models (LLMs) face constraints due to the quadratic complexity of the self-attention mechanism. The mainstream sequence parallelism (SP) method, Ring Attention, attempts to solve this by distributing the query into multiple query chunks across accelerators and enable each Q tensor to access all KV tensors from other accelerators via the Ring AllGather communication primitive. However, it exhibits low communication efficiency, restricting its practical applicability. This inefficiency stems from the mismatch between the Ring AllGather communication primitive it adopts and the AlltoAll topology of modern accelerators. A Ring AllGather primitive is composed of iterations of ring-styled data transfer, which can only utilize a very limited fraction of an AlltoAll topology. Inspired by the Hamiltonian decomposition of complete directed graphs, we identify that modern accelerator topology can be decomposed into multiple orthogonal ring datapaths which can concurrently transfer data without interference. Based on this, we further observe that the Ring AllGather primitive can also be decomposed into the same number of concurrent ring-styled data transfer at every iteration. Based on these insights, we propose TASP, a topology-aware SP method for long-context LLMs that fully utilizes the communication capacity of modern accelerators via topology decomposition and primitive decomposition. Experimental results on both single-node and multi-node NVIDIA H100 systems and a single-node AMD MI300X system demonstrate that TASP achieves higher communication efficiency than Ring Attention on these modern accelerator topologies and achieves up to 3.58 speedup than Ring Attention and its variant Zigzag-Ring Attention. The code is available at https://github.com/infinigence/HamiltonAttention.

cs.LG↗

arXiv2025

Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering

Generative models have achieved remarkable success across various applications, driving the demand for multi-GPU computing. Inter-GPU communication becomes a bottleneck in multi-GPU computing systems, particularly on consumer-grade GPUs. By exploiting concurrent hardware execution, overlapping computation and communication latency becomes an effective technique for mitigating the communication overhead. We identify that an efficient and adaptable overlapping design should satisfy (1) tile-wise overlapping to maximize the overlapping opportunity, (2) interference-free computation to maintain the original computational performance, and (3) communication agnosticism to reduce the development burden against varying communication primitives. Nevertheless, current designs fail to simultaneously optimize for all of those features. To address the issue, we propose FlashOverlap, which utilizes a novel signaling mechanism: when part of the output finishes, the computation kernel sends a signal to trigger the communication of that part, while continuing the computation of the remaining part (interference-free computation). Consequently, the communication of the finished part and the computation of the remaining part can be overlapped. On top of the signaling mechanism, FlashOverlap comprises two key components: (1) the determination of the signaling timing to boost the overlap efficiency (tile-wise overlapping), and (2) a pre-communication reordering to create the contiguous address for finished data, enabling communication by simply calling NCCL APIs (communication agnosticism), and a post-communication reordering to correct the data order. Experiments show that FlashOverlap achieves up to 1.65x speedup through overlap, outperforming existing works in most cases. Code is available at https://github.com/infinigence/FlashOverlap.

cs.DC↗

arXiv2025

FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on importance metrics, such as cumulative attention scores. However, even important tokens may exhibit high redundancy caused by similarity among adjacent video frames and repetitive visual elements. To address this limitation, we propose FrameFusion, a novel token reduction approach integrating similarity-based merging with importance-based pruning. We conduct a thorough study on token similarity characteristics, revealing three key insights: (1) spatially corresponding visual tokens between adjacent frames have higher cosine similarities compared to other token pairs; (2) high token similarities prominently decrease in deeper model layers; and (3) token similarity rankings are highly consistent across different layers. Guided by these observations, FrameFusion computes token similarities exclusively between corresponding visual tokens from adjacent frames, applies token merging at initial successive layers followed by pruning in deeper layers, and adopts a cascaded merging strategy to further enhance efficiency. We evaluate FrameFusion comprehensively across six diverse LVLMs, ranging from 2B to 72B parameters, using five video benchmarks encompassing video retrieval, question-answering, and spatial-temporal understanding tasks. Experiments show that FrameFusion reduces visual tokens by 70%, achieving 1.6-3.6x end-to-end speedups, with an average performance impact of less than 3%. Our code is available at: https://github.com/thu-nics/FrameFusion.

cs.CV↗

arXiv2025

Megrez2 Technical Report

We present Megrez2, a novel lightweight and high-performance language model architecture optimized for device native deployment. Megrez2 introduces a novel cross-layer expert sharing mechanism, which significantly reduces total parameter count by reusing expert modules across adjacent transformer layers while maintaining most of the model's capacity. It also incorporates pre-gated routing, enabling memory-efficient expert loading and faster inference. As the first instantiation of the Megrez2 architecture, we introduce the Megrez2-Preview model, which is pre-trained on a 5-trillion-token corpus and further enhanced through supervised fine-tuning and reinforcement learning with verifiable rewards. With only 3B activated and 7.5B stored parameters, Megrez2-Preview demonstrates competitive or superior performance compared to larger models on a wide range of tasks, including language understanding, instruction following, mathematical reasoning, and code generation. These results highlight the effectiveness of the Megrez2 architecture to achieve a balance between accuracy, efficiency, and deployability, making it a strong candidate for real-world, resource-constrained applications.

cs.CL↗

arXiv2025

Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective

Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLMs like BERT and DeBERTa, generative LLMs like GPT series and Llama series are currently the main focus due to their superior algorithmic performance. The advancements in generative LLMs are closely intertwined with the development of hardware capabilities. Various hardware platforms exhibit distinct hardware characteristics, which can help improve LLM inference performance. Therefore, this paper comprehensively surveys efficient generative LLM inference on different hardware platforms. First, we provide an overview of the algorithm architecture of mainstream generative LLMs and delve into the inference process. Then, we summarize different optimization methods for different platforms such as CPU, GPU, FPGA, ASIC, and PIM/NDP, and provide inference results for generative LLMs. Furthermore, we perform a qualitative and quantitative comparison of inference performance with batch sizes 1 and 8 on different hardware platforms by considering hardware power consumption, absolute inference speed (tokens/s), and energy efficiency (tokens/J). We compare the performance of the same optimization methods across different hardware platforms, the performance across different hardware platforms, and the performance of different methods on the same hardware platform. This provides a systematic and comprehensive summary of existing inference acceleration work by integrating software optimization methods and hardware platforms. We point out that three trends (multimodality, inference-time compute, and higher inference energy efficiency) are promising to redefine the capabilities of edge artificial intelligence systems. Our project is available at https://dai.sjtu.edu.cn/project.html.

cs.AR↗

arXiv2025

DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

Circuit representation learning has become pivotal in electronic design automation, enabling critical tasks such as testability analysis, logic reasoning, power estimation, and SAT solving. However, existing models face significant challenges in scaling to large circuits due to limitations like over-squashing in graph neural networks and the quadratic complexity of transformer-based models. To address these issues, we introduce DeepGate4, a scalable and efficient graph transformer specifically designed for large-scale circuits. DeepGate4 incorporates several key innovations: (1) an update strategy tailored for circuit graphs, which reduce memory complexity to sub-linear and is adaptable to any graph transformer; (2) a GAT-based sparse transformer with global and local structural encodings for AIGs; and (3) an inference acceleration CUDA kernel that fully exploit the unique sparsity patterns of AIGs. Our extensive experiments on the ITC99 and EPFL benchmarks show that DeepGate4 significantly surpasses state-of-the-art methods, achieving 15.5% and 31.1% performance improvements over the next-best models. Furthermore, the Fused-DeepGate4 variant reduces runtime by 35.1% and memory usage by 46.8%, making it highly efficient for large-scale circuit analysis. These results demonstrate the potential of DeepGate4 to handle complex EDA tasks while offering superior scalability and efficiency. Code is available at https://github.com/zyzheng17/DeepGate4-ICLR-25.

cs.LG↗

arXiv2025

semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a disaggregated system where the two phases are disaggregated to different GPUs. The design of the disaggregated system addresses the latency interference and sophisticated scheduling issues in the unified system but leads to storage challenges including 1) replicated weights for both phases that prevent flexible deployment, 2) KV cache transfer overhead between the two phases, 3) storage imbalance that causes substantial wasted space of the GPU capacity, and 4) suboptimal resource adjustment arising from the difficulties in migrating KV cache. Such storage inefficiency delivers poor serving performance under high request rates. In this paper, we identify that the advantage of the disaggregated system lies in the disaggregated computation, i.e., partitioning the computational resource to enable the asynchronous computation of two phases. Thus, we propose a novel LLM serving system, semi-PD, characterized by disaggregated computation and unified storage. In semi-PD, we introduce a computation resource controller to achieve disaggregated computation at the streaming multi-processor (SM) level, and a unified memory manager to manage the asynchronous memory access from both phases. semi-PD has a low-overhead resource adjustment mechanism between the two phases, and a service-level objective (SLO) aware dynamic partitioning algorithm to optimize the SLO attainment. Compared to state-of-the-art systems, semi-PD maintains lower latency at higher request rates, reducing the average end-to-end latency per request by 1.27-2.58x on DeepSeek series models, and serves 1.55-1.72x more requests adhering to latency constraints on Llama series models.

cs.CL↗

arXiv2025

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal non-uniformity of real-world videos and observe that videos exhibit dynamic information density, with high-motion segments demanding greater detail preservation than static scenes. Inspired by this temporal non-uniformity, we propose VGDFR, a training-free approach for Diffusion-based Video Generation with Dynamic Latent Frame Rate. VGDFR adaptively adjusts the number of elements in latent space based on the motion frequency of the latent space content, using fewer tokens for low-frequency segments while preserving detail in high-frequency segments. Specifically, our key contributions are: (1) A dynamic frame rate scheduler for DiT video generation that adaptively assigns frame rates for video segments. (2) A novel latent-space frame merging method to align latent representations with their denoised counterparts before merging those redundant in low-resolution space. (3) A preference analysis of Rotary Positional Embeddings (RoPE) across DiT layers, informing a tailored RoPE strategy optimized for semantic and local information capture. Experiments show that VGDFR can achieve a speedup up to 3x for video generation with minimal quality degradation.

cs.CV↗