More Like this

1. When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

   You, Haoran; Fu, Yichao; Wang, Zheng; Yazdanbakhsh, Amir; Lin, Yingyan Celine (July 2024, Proceedings of Machine Learning Research)

   Lawrence, Neil (Ed.)

   Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited efficiency due to the sequential processing nature of autoregressive LLMs during generation. While linear attention and speculative decoding offer potential solutions, their applicability and synergistic potential for enhancing autoregressive LLMs remain uncertain. We conduct the first comprehensive study on the efficacy of existing linear attention methods for autoregressive LLMs, integrating them with speculative decoding. We introduce an augmentation technique for linear attention that ensures compatibility with speculative decoding, enabling more efficient training and serving of LLMs. Extensive experiments and ablation studies involving seven existing linear attention models and five encoder/decoder-based LLMs consistently validate the effectiveness of our augmented linearized LLMs. Notably, our approach achieves up to a 6.67 reduction in perplexity on the LLaMA model and up to a 2× speedup during generation compared to prior linear attention methods. Codes and models are available at https://github.com/GATECH-EIC/Linearized-LLM. 

   more » « less
2. SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding

   Sandler, Jameson; Christopher, Jacob K; Hartvigsen, Thomas; Fioretto, Ferdinando (April 2026, Conference on Machine Learning and Systems (MLSys))

   Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive speed-ups. Yet, current speculative decoding approaches remain limited by two fundamental bottlenecks: (1) the autoregressive dependency during drafting which limits parallelism, and (2) frequent rejections of draft tokens caused by misalignment between the draft and verify models. This paper proposes SpecDiff-2, a novel framework to jointly address these two bottlenecks. It leverages discrete diffusion as a non-autoregressive drafter to address bottleneck (1) and develops novel techniques to calibrate discrete diffusion drafters with autoregressive verifiers, addressing bottleneck (2). Experimental results across a comprehensive benchmark suite show that SpecDiff-2 achieves a new state-of-the-art across reasoning, coding, and mathematical benchmarks, improving tokens-per-second by up to an average of +55% over previous baselines and obtaining up to 5.5x average speed-up over standard decoding, without any loss of accuracy. 

   more » « less
3. Dynamic-Width Speculative Beam Decoding for LLM Inference

   https://doi.org/10.1609/aaai.v39i23.34690  

   Qin, Zongyue; He, Zifan; Prakriya, Neha; Cong, Jason; Sun, Yizhou (April 2025, Proceedings of the AAAI Conference on Artificial Intelligence)

   Large language models (LLMs) based on transformer architecture have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slow and costly. Speculative decoding has emerged as a promising solution, leveraging a smaller auxiliary model to draft future tokens, which are then validated simultaneously by the larger model, achieving a speed-up of 1-2x. Although speculative decoding matches the same distribution as multinomial sampling, multinomial sampling itself is prone to suboptimal outputs, where as beam sampling is widely recognized for producing higher-quality results by maintaining multiple candidate sequences at each step.This paper explores the novel integration of speculative decoding with beam sampling. However, there are four key challenges: (1) how to generate multiple sequences from the larger model's distribution given drafts sequences from the small model; (2) how to dynamically optimize the number of beams to balance efficiency and accuracy; (3) how to efficiently verify the multiple drafts in parallel; and (4) how to address the extra memory costs inherent in beam sampling.To address these challenges, we propose dynamic-width speculative beam decoding (DSBD). Specifically, we first introduce a novel draft and verification scheme that generates multiple sequences following the large model's distribution based on beam sampling trajectories from the small model. Then, we introduce an adaptive mechanism to dynamically tune the number of beams based on the context, optimizing efficiency and effectiveness. Besides, we extend tree-based parallel verification to handle multiple trees simultaneously, accelerating the verification process. Finally, we illustrate a simple modification to our algorithm to mitigate the memory overhead of beam sampling.Experimental results show that our approach achieves a 1.5-1.9x speed-up and1.8-2.5x lower energy consumption compared to beam sampling, with no loss in downstream performance. Moreover, it can produce significantly higher-quality outputs than speculative decoding, while maintaining similar time, memory, and energy costs. In summary, our method offers a more efficient and effective inference process for LLMs. 

   more » « less
4. From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

   Welleck, Sean; Bertsch, Amanda; Finlayson, Matthew; Schoelkopf, Hailey; Xie, Alex; Neubig, Graham; Kulikov, Ilia; Harchaoui, Zaid (November 2024, https://doi.org/10.48550/arXiv.2406.16838 Focus to learn more)

   One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during inference. This survey focuses on these inference-time approaches. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation. Token-level generation algorithms, often called decoding algorithms, operate by sampling a single token at a time or constructing a token-level search space and then selecting an output. These methods typically assume access to a language model's logits, next-token distributions, or probability scores. Meta-generation algorithms work on partial or full sequences, incorporating domain knowledge, enabling backtracking, and integrating external information. Efficient generation methods aim to reduce token costs and improve the speed of generation. Our survey unifies perspectives from three research communities: traditional natural language processing, modern LLMs, and machine learning systems. 

   more » « less
5. TeLLMe v2: An Efficient End-to-End Ternary LLM Prefill and Decode Accelerator with Table-Lookup Matmul on Edge FPGAs

   Qiao, Ye; Chen, Zhiheng; Zhang, Yifan; Wang, Yian; Huang, Sitao (October 2025, arXiv)

   With the emergence of wearable devices and other embedded systems, deploying large language models (LLMs) on edge platforms has become an urgent need. However, this is challenging because of their high computational and memory demands. Although recent low-bit quantization methods (e.g., BitNet, DeepSeek) compress weights to as low as 1.58~bits with minimal accuracy loss, edge deployment is still constrained by limited on-chip resources, power budgets, and the often-neglected long latency of the prefill stage. We present TeLLMe, the first table-lookup-based ternary LLM accelerator for low-power edge FPGAs that fully supports both prefill and autoregressive decoding using 1.58-bit weights and 8-bit activations. TeLLMe incorporates several novel techniques, including (1) a table-lookup-based ternary matrix multiplication (TLMM) engine utilizing grouped activations and online precomputation for low resource utilization and high throughput; (2) a fine-grained analytic URAM-based weight buffer management scheme for efficient loading and compute engine access; (3) a streaming dataflow architecture that fuses floating-point element-wise operations with linear computations to hide latency; (4) a reversed-reordered prefill stage attention with fused attention operations for high memory efficiency; and (5) a resource-efficient specialized decoding stage attention. Under a 5~W power budget, TeLLMe delivers up to 25~tokens/s decoding throughput and 0.45--0.96~s time-to-first-token (TTFT) for 64--128 token prompts, marking a significant energy-efficiency advancement in LLM inference on edge FPGAs. 

   more » « less