arXiv subjects

Souvik Kundu

Publications and source records attributed to Souvik Kundu.

At least 55 records · Page 3Linked to original sources

arXiv2025

SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. However, recent studies reveal substantial redundancy in the CoT reasoning traces, which not only increases inference latency but also negatively impacts model performance by diverting attention to unnecessary reasoning paths. To address this issue, we investigate the internal reasoning structures of LLMs and categorize them into three primary thought types: execution, reflection, and transition thoughts. Moreover, our analysis reveals that excessive reflection and transition thoughts are strongly correlated with failure cases and these thought categories exhibit clear separation in the latent space. Based on these, we introduce SEAL (Steerable reasoning calibration), a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains. SEAL consists of an offline stage for extracting the reasoning steering vector in the latent space, followed by an on-the-fly calibration of the reasoning trace through representation intervention using the steering vector. Notably, the steering vector exhibits strong transferability across various tasks. Extensive experiments across multiple models (DeepSeek-R1-Distill and QwQ-32B-Preview) and benchmarks (Math500, GSM8K, LiveCodeBench) validate the effectiveness of SEAL, up to a 11% improvement in accuracy while reducing reasoning tokens by 11.8% to 50.4%. Our code is publicly available at https://github.com/VITA-Group/SEAL.

cs.CL↗

arXiv2025

Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression

Despite their remarkable progress in multimodal understanding tasks, large vision language models (LVLMs) often suffer from "hallucinations", generating texts misaligned with the visual context. Existing methods aimed at reducing hallucinations through inference time intervention incur a significant increase in latency. To mitigate this, we present SPIN, a task-agnostic attention-guided head suppression strategy that can be seamlessly integrated during inference, without incurring any significant compute or latency overhead. We investigate whether hallucination in LVLMs can be linked to specific model components. Our analysis suggests that hallucinations can be attributed to a dynamic subset of attention heads in each layer. Leveraging this insight, for each text query token, we selectively suppress attention heads that exhibit low attention to image tokens, keeping the top-K attention heads intact. Extensive evaluations on visual question answering and image description tasks demonstrate the efficacy of SPIN in reducing hallucination scores up to 2.7x while maintaining F1, and improving throughput by 1.8x compared to existing alternatives. Code is available at https://github.com/YUECHE77/SPIN.

cs.CV↗

arXiv2025

Flux confinement-deconfinement transition of dimer-loop models on three-dimensional bipartite lattices

Motivated by recent work that mapped the low-temperature properties of a class of frustrated spin $S=1$ kagome antiferromagnets with competing exchange and single-ion anisotropies to the fully-packed limit (with each vertex touched by exactly one dimer or nontrivial loop) of a system of dimers and nontrivial (length $s > 2$) loops on the honeycomb lattice, we study this fully-packed dimer-loop model on the three-dimensional bipartite cubic and diamond lattices as a function of $w$, the relative fugacity of dimers. We find that the $w \rightarrow 0$ O($1$) loop-model limit is separated from the $w \rightarrow \infty$ dimer limit by a geometric phase transition at a nonzero finite critical fugacity $w_c$: The $w>w_c$ phase has short loops with an exponentially decaying loop-size distribution, while the $w w_c$, but become deconfined in the small-$w$ phase. Although both phases are unstable to a nonzero fugacity for the charge $\pm 1/2$ excitations, the destruction of the $w >w_c$ Coulomb liquid is characterized by an interesting slow crossover, since test charges with $q=\pm 1/2$ are confined in this phase.

cond-mat.stat-mech↗

arXiv2025

CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

Large language models have achieved remarkable success in various tasks but suffer from high computational costs during inference, limiting their deployment in resource-constrained applications. To address this issue, we propose a novel Collaborative Inference with Token-lEvel Routing (CITER) framework that enables efficient collaboration between small and large language models (SLMs \& LLMs) through a token-level routing strategy. Specifically, CITER routes non-critical tokens to an SLM for efficiency and routes critical tokens to an LLM for generalization quality. We formulate router training as a policy optimization, where the router receives rewards based on both the quality of predictions and the inference costs of generation. This allows the router to learn to predict token-level routing scores and make routing decisions based on both the current token and the future impact of its decisions. To further accelerate the reward evaluation process, we introduce a shortcut which significantly reduces the costs of the reward estimation and improving the practicality of our approach. Extensive experiments on five benchmark datasets demonstrate that CITER reduces the inference costs while preserving high-quality generation, offering a promising solution for real-time and resource-constrained applications. Our data and code are available at https://github.com/aiming-lab/CITER.

cs.CL↗

arXiv2025

MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models

Diffusion-based text-to-image generation models trade latency for quality: small models are fast but generate lower-quality images, while large models produce better images but are slow. We present MoDM, a novel caching-based serving system for diffusion models that dynamically balances latency and quality through a mixture of diffusion models. Unlike prior approaches that rely on model-specific internal features, MoDM caches final images, allowing seamless retrieval and reuse across multiple diffusion model families. This design enables adaptive serving by dynamically balancing latency and image quality: using smaller models for cache-hit requests to reduce latency while reserving larger models for cache-miss requests to maintain quality. Small model image quality is preserved using retrieved cached images. We design a global monitor that optimally allocates GPU resources and balances inference workload, ensuring high throughput while meeting service-level objectives under varying request rates. Our evaluations show that MoDM significantly reduces average serving time by 2.5x while retaining image quality, making it a practical solution for scalable and resource-efficient model deployment.

cs.DC↗

arXiv2025

On Evaluating Performance of LLM Inference Serving Systems

The rapid evolution of Large Language Model (LLM) inference systems has yielded significant efficiency improvements. However, our systematic analysis reveals that current evaluation methodologies frequently exhibit fundamental flaws, often manifesting as common evaluation anti-patterns that obscure true performance characteristics and impede scientific progress. Through a comprehensive examination of recent systems, we identify recurring anti-patterns across three key dimensions: Baseline Fairness, Evaluation Setup, and Metric Design. These anti-patterns are uniquely problematic for LLM inference due to its dual-phase nature combining distinct prefill and decode operations, its handling of highly heterogeneous workloads, and its strict temporal requirements for interactive use. We demonstrate how common anti-patterns -- such as inadequate baseline comparisons that conflate engineering effort with algorithmic novelty, workload selections that fail to represent production scenarios, and metric normalizations that hide substantial performance variability like generation stalls-lead to misleading conclusions. To address these challenges, we provide a comprehensive checklist derived from our analysis, establishing a framework for recognizing and avoiding these anti-patterns in favor of robust LLM inference evaluation. To demonstrate the practical application of our framework, we present a case study analyzing speculative decoding, a technique whose bursty, non-uniform token generation is easily misinterpreted when evaluated using approaches characteristic of these anti-patterns. Our work establishes a rigorous foundation for evaluation methodology, enabling meaningful comparisons, ensuring reproducible results, and ultimately accelerating genuine progress in LLM inference systems by moving beyond common anti-patterns to align evaluation with real-world requirements.

cs.LG↗

arXiv2025

GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs

Large Language Models (LLMs) have revolutionized natural language processing (NLP), excelling in tasks like text generation and summarization. However, their increasing adoption in mission-critical applications raises concerns about hardware-based threats, particularly bit-flip attacks (BFAs). BFAs, enabled by fault injection methods such as Rowhammer, target model parameters in memory, compromising both integrity and performance. Identifying critical parameters for BFAs in the vast parameter space of LLMs poses significant challenges. While prior research suggests transformer-based architectures are inherently more robust to BFAs compared to traditional deep neural networks, we challenge this assumption. For the first time, we demonstrate that as few as three bit-flips can cause catastrophic performance degradation in an LLM with billions of parameters. Current BFA techniques are inadequate for exploiting this vulnerability due to the difficulty of efficiently identifying critical parameters within the immense parameter space. To address this, we propose AttentionBreaker, a novel framework tailored for LLMs that enables efficient traversal of the parameter space to identify critical parameters. Additionally, we introduce GenBFA, an evolutionary optimization strategy designed to refine the search further, isolating the most critical bits for an efficient and effective attack. Empirical results reveal the profound vulnerability of LLMs to AttentionBreaker. For example, merely three bit-flips (4.129 x 10^-9% of total parameters) in the LLaMA3-8B-Instruct 8-bit quantized (W8) model result in a complete performance collapse: accuracy on MMLU tasks drops from 67.3% to 0%, and Wikitext perplexity skyrockets from 12.6 to 4.72 x 10^5. These findings underscore the effectiveness of AttentionBreaker in uncovering and exploiting critical vulnerabilities within LLM architectures.

cs.CR↗

arXiv2025

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they often degrade accuracy due to overemphasizing recent tokens. In this work, we first propose dual-state linear attention (DSLA), a novel design that maintains two specialized hidden states-one for preserving historical context and one for tracking recency-thereby mitigating the short-range bias typical of linear-attention architectures. To further balance efficiency and accuracy under dynamic workload conditions, we introduce DSLA-Serve, an online adaptive distillation framework that progressively replaces Transformer layers with DSLA layers at inference time, guided by a sensitivity-based layer ordering. DSLA-Serve uses a chained fine-tuning strategy to ensure that each newly converted DSLA layer remains consistent with previously replaced layers, preserving the overall quality. Extensive evaluations on commonsense reasoning, long-context QA, and text summarization demonstrate that DSLA-Serve yields 2.3x faster inference than Llama2-7B and 3.0x faster than the hybrid Zamba-7B, while retaining comparable performance across downstream tasks. Our ablation studies show that DSLA's dual states capture both global and local dependencies, addressing the historical-token underrepresentation seen in prior linear attentions. Codes are available at https://github.com/utnslab/DSLA-Serve.

cs.LG↗

arXiv2025

Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection

Parameter Efficient Fine-Tuning (PEFT) has become the de-facto approach in adapting Large Language Models (LLMs) for downstream tasks in Natural Language Processing. However, its adoption in privacy-preserving distributed learning frameworks, such as Federated Learning (FL), remains relatively limited. This is mainly due to challenges specific to FL, such as resource-constrained devices and diverse data distributions among clients. In this paper, we propose an efficient method to perform PEFT within the FL framework for Multi-Head Attention (MHA) based language models. We address the challenges through head pruning, a novel head-specific weighted aggregation mechanism, and a client selection strategy. Head pruning minimizes training complexity within the clients, guided by the importance score computed based on the confidence of the attention head. Weighted aggregation of heads ensures the global model captures crucial updates from diverse clients complementing our client selection strategy. We show results on the MultiNLI benchmark along with 20 Newsgroups, XL-Sum, and E2E NLG datasets. We use the MultiNLI dataset and T5-small model with LoRA as our PEFT method, attaining sparsity levels of up to 90%, resulting in a communication advantage of up to 1.8x and a reduction in training OPs of 3.9x while maintaining the accuracy drop under 2%.

cs.CL↗

arXiv2025

Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits

Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots. However, their deployment often depends on expensive cloud-based APIs, creating high operational costs, which limit access for smaller organizations and raise sustainability concerns. Certain LLMs can be deployed on-device, offering a cost-effective solution with reduced latency and improved privacy. Yet, limited computing resources constrain the size and accuracy of models that can be deployed, necessitating a collaborative design between edge and cloud. We propose a fast and cost-effective speculative edge-cloud decoding framework with a large target model on the server and a small draft model on the device. By introducing early exits in the target model, tokens are generated mid-verification, allowing the client to preemptively draft subsequent tokens before final verification, thus utilizing idle time and enhancing parallelism between edge and cloud. Using an NVIDIA Jetson Nano (client) and an A100 GPU (server) with Vicuna-68M (draft) and Llama2-7B (target) models, our method achieves up to a 35% reduction in latency compared to cloud-based autoregressive decoding, with an additional 11% improvement from preemptive drafting. To demonstrate real-world applicability, we deploy our method on the Unitree Go2 quadruped robot using Vision-Language Model (VLM) based control, achieving a 21% speedup over traditional cloud-based autoregressive decoding. These results demonstrate the potential of our framework for real-time LLM and VLM applications on resource-constrained edge devices.

cs.RO↗

arXiv2025

Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale

Zeroth-order (ZO) optimization has emerged as a promising alternative to gradient-based backpropagation methods, particularly for black-box optimization and large language model (LLM) fine-tuning. However, ZO methods often suffer from slow convergence due to high-variance stochastic gradient estimators. While subspace perturbations, such as sparsity and low-rank constraints, have been explored to mitigate this issue, their effectiveness remains poorly understood. In this work, we develop a \emph{unified theoretical framework} that analyzes both the convergence and generalization properties of ZO optimization under subspace perturbations. We show that high dimensionality is the primary bottleneck and introduce the notion of \textit{subspace alignment} to explain how the subspace perturbations reduce gradient noise and accelerate convergence. Our analysis further shows that a broad class of subspace perturbations exhibits a similar convergence rate, motivating us to prioritize practical considerations in real-world algorithm design. Building on these insights, we propose an efficient ZO method using block coordinate descent (MeZO-BCD), which perturbs and updates only a subset of parameters at each step. Extensive experiments show that MeZO-BCD significantly accelerates optimization, achieving up to $\mathbf{\times2.77}$ speedup in wall-clock time over MeZO on OPT-13B, while maintaining comparable iteration complexity and fine-tuning performance.

cs.LG↗

arXiv2025

Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models

Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these gigantic models efficiently for diverse inference use cases requires carefully designed hardware platforms with ample computing, memory, and network resources. With constant innovation in LLM serving optimizations and model architecture evolving at breakneck speed, the hardware requirements to meet Service Level Objectives (SLOs) remain an open research question. To answer the question, we present an analytical tool, GenZ, to efficiently navigate the relationship between diverse LLM model architectures(Dense, GQA, MoE, Mamba), LLM serving optimizations(Chunking, Speculative decoding, quanitization), and AI platform design parameters. Our tool estimates LLM inference performance metrics for the given scenario. We have validated against real hardware platforms running various different LLM models, achieving a max geomean error of 5.82.We use GenZ to identify compute, memory capacity, memory bandwidth, network latency, and network bandwidth requirements across diverse LLM inference use cases. We also study diverse architectural choices in use today (inspired by LLM serving platforms from several vendors) to help inform computer architects designing next-generation AI hardware accelerators and platforms. The trends and insights derived from GenZ can guide AI engineers deploying LLMs as well as computer architects designing next-generation hardware accelerators and platforms. Ultimately, this work sheds light on the platform design considerations for unlocking the full potential of large language models across a spectrum of applications. The source code is available at https://github.com/abhibambhaniya/GenZ-LLM-Analyzer . Users can also be tried it on at https://genz-llm-analyzer.streamlit.app/ without any setup on your web browser.

cs.AR↗

arXiv2025

MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization

Quantization of foundational models (FMs) is significantly more challenging than traditional DNNs due to the emergence of large magnitude values called outliers. Existing outlier-aware algorithm-architecture co-design techniques either use mixed-precision, retaining outliers at high precision but compromise hardware efficiency, or quantize inliers and outliers at the same precision, improving hardware efficiency at the cost of accuracy. To address this mutual exclusivity, we propose MicroScopiQ, a novel co-design technique that leverages pruning to complement outlier-aware quantization. MicroScopiQ retains outliers at higher precision while pruning a certain fraction of least important weights to distribute the additional outlier bits; ensuring high accuracy, aligned memory and hardware efficiency. We design a high-throughput, low overhead accelerator architecture composed of multi-precision INT processing elements and a network-on-chip called ReCoN that efficiently abstracts the complexity of supporting high-precision outliers. Additionally, unlike prior techniques, MicroScopiQ does not assume any locality of outlier weights, enabling applicability to a broad range of FMs. Extensive experiments across diverse quantization settings demonstrate that MicroScopiQ achieves state-of-the-art quantization accuracy, while delivering up to 3x faster inference and 2x lower energy consumption compared to existing alternatives. Code is available at: https://github.com/georgia-tech-synergy-lab/MicroScopiQ-LLM-Quantization

cs.AR↗

arXiv2025

Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator

Large language model (LLM) pruning with fixed N:M structured sparsity significantly limits the expressivity of the sparse model, yielding sub-optimal performance. In contrast, supporting multiple N:M patterns to provide sparse representational freedom introduces costly overhead in hardware. To address these challenges for LLMs, we first present a flexible layer-wise outlier-density-aware N:M sparsity (FLOW) selection method. FLOW enables the identification of optimal layer-wise N and M values (from a given range) by simultaneously accounting for the presence and distribution of outliers, allowing a higher degree of representational freedom. To deploy sparse models with such N:M flexibility, we then introduce a flexible, low-overhead digital compute-in-memory architecture (FlexCiM). FlexCiM supports diverse sparsity patterns by partitioning a digital CiM (DCiM) macro into smaller sub-macros, which are adaptively aggregated and disaggregated through distribution and merging mechanisms for different N and M values. Extensive experiments on both transformer-based and recurrence-based state space foundation models (SSMs) demonstrate that FLOW outperforms existing alternatives with an accuracy improvement of up to 36%, while FlexCiM achieves up to 1.75x lower inference latency and 1.5x lower energy consumption compared to existing sparse accelerators. Code is available at: https://github.com/FLOW-open-project/FLOW

cs.LG↗

arXiv2025

LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models

Speculative decoding has been widely used to accelerate auto-regressive (AR) text generation. However, its effectiveness for visual AR models remains limited due to token selection ambiguity, where multiple tokens share similarly low probabilities and thus reduce acceptance rates. Recently, relaxed speculative decoding with dynamic tree drafting was proposed to mitigate this ambiguity, demonstrating promising results in accelerating visual AR models. However, we observe that token selection ambiguity still negatively affects dynamic tree drafting, resulting in shallow draft trees and limited acceleration. To overcome this issue, we introduce LANTERN++, a refined framework that integrates static tree drafting with a tailored relaxed acceptance condition, allowing drafts to be selected independently of low-confidence predictions. This enables the acceptance of deeper sequences, improving decoding efficiency while preserving image quality. Extensive experiments on state-of-the-art visual AR models demonstrate that LANTERN++ significantly accelerates inference, achieving up to $\mathbf{\times 2.56}$ speedup over standard AR decoding while maintaining high image quality. The code is publicly available at https://github.com/jadohu/LANTERN.

cs.CV↗

arXiv2025

Enhancing Large Language Models for Hardware Verification: A Novel SystemVerilog Assertion Dataset

Hardware verification is crucial in modern SoC design, consuming around 70% of development time. SystemVerilog assertions ensure correct functionality. However, existing industrial practices rely on manual efforts for assertion generation, which becomes increasingly untenable as hardware systems become complex. Recent research shows that Large Language Models (LLMs) can automate this process. However, proprietary SOTA models like GPT-4o often generate inaccurate assertions and require expensive licenses, while smaller open-source LLMs need fine-tuning to manage HDL code complexities. To address these issues, we introduce **VERT**, an open-source dataset designed to enhance SystemVerilog assertion generation using LLMs. VERT enables researchers in academia and industry to fine-tune open-source models, outperforming larger proprietary ones in both accuracy and efficiency while ensuring data privacy through local fine-tuning and eliminating costly licenses. The dataset is curated by systematically augmenting variables from open-source HDL repositories to generate synthetic code snippets paired with corresponding assertions. Experimental results demonstrate that fine-tuned models like Deepseek Coder 6.7B and Llama 3.1 8B outperform GPT-4o, achieving up to 96.88% improvement over base models and 24.14% over GPT-4o on platforms including OpenTitan, CVA6, OpenPiton and Pulpissimo. VERT is available at https://github.com/AnandMenon12/VERT.

cs.LG↗

arXiv2025

LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression

Despite recent efforts in understanding the compression impact on large language models (LLMs) in terms of their downstream task performance and trustworthiness on relatively simpler uni-modal benchmarks (for example, question answering, common sense reasoning), their detailed study on multi-modal Large Vision-Language Models (LVLMs) is yet to be unveiled. Towards mitigating this gap, we present LVLM-Compress-Bench, a framework to first thoroughly study the broad impact of compression on the generative performance of LVLMs with multi-modal input driven tasks. In specific, we consider two major classes of compression for autoregressive models, namely KV cache and weight compression, for the dynamically growing intermediate cache and static weights, respectively. We use four LVLM variants of the popular LLaVA framework to present our analysis via integrating various state-of-the-art KV and weight compression methods including uniform, outlier-reduced, and group quantization for the KV cache and weights. With this framework we demonstrate on ten different multi-modal datasets with different capabilities including recognition, knowledge, language generation, spatial awareness, visual reasoning, hallucination and visual illusion identification, toxicity, stereotypes and bias. In specific, our framework demonstrates the compression impact on both general and ethically critical metrics leveraging a combination of real world and synthetic datasets to encompass diverse societal intersectional attributes. Extensive experimental evaluations yield diverse and intriguing observations on the behavior of LVLMs at different quantization budget of KV and weights, in both maintaining and losing performance as compared to the baseline model with FP16 data format. Code will be open-sourced at https://github.com/opengear-project/LVLM-compress-bench.

cs.CV↗

arXiv2025

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitation of AR models is their sequential nature, which processes tokens one at a time, slowing down generation compared to models like GANs or diffusion-based methods that operate more efficiently. While speculative decoding has proven effective for accelerating LLMs by generating multiple tokens in a single forward, its application in visual AR models remains largely unexplored. In this work, we identify a challenge in this setting, which we term \textit{token selection ambiguity}, wherein visual AR models frequently assign uniformly low probabilities to tokens, hampering the performance of speculative decoding. To overcome this challenge, we propose a relaxed acceptance condition referred to as LANTERN that leverages the interchangeability of tokens in latent space. This relaxation restores the effectiveness of speculative decoding in visual AR models by enabling more flexible use of candidate tokens that would otherwise be prematurely rejected. Furthermore, by incorporating a total variation distance bound, we ensure that these speed gains are achieved without significantly compromising image quality or semantic coherence. Experimental results demonstrate the efficacy of our method in providing a substantial speed-up over speculative decoding. In specific, compared to a naïve application of the state-of-the-art speculative decoding, LANTERN increases speed-ups by $\mathbf{1.75}\times$ and $\mathbf{1.82}\times$, as compared to greedy decoding and random sampling, respectively, when applied to LlamaGen, a contemporary visual AR model. The code is publicly available at https://github.com/jadohu/LANTERN.

cs.CV↗