Related papers: Wide-In, Narrow-Out: Revokable Decoding for Effici…
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…
Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number…
Speculative decoding has emerged as a promising technique for large language model (LLM) inference by accelerating autoregressive decoding via draft-then-verify. This paper studies a new edge scenario with multi-user inference, where draft…
Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…
Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token…
Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede…
We propose Windowed Inference for Non-blank Detection (WIND), a novel strategy that significantly accelerates RNN-T inference without compromising model accuracy. During model inference, instead of processing frames sequentially, WIND…
Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniques accelerate…
Beyond parallel generation and global context modeling, current masked diffusion large language models (masked dLLMs, i.e., LLaDA) suffer from a fundamental limitation: they require a predefined, fixed generation length, which lacks…
We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs). First, during training we apply layer dropout, with low dropout rates for earlier layers and higher dropout rates for later layers, and an…
Large vision-language models (LVLMs) excel at multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We present DROPOUT DECODING, a novel inference-time approach that…
In this work, we present Xwin-LM, a comprehensive suite of alignment methodologies for large language models (LLMs). This suite encompasses several key techniques, including supervised finetuning (SFT), reward modeling (RM), rejection…
In this work, we provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs). Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel…
Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere…
Generative inference in Large Language Models (LLMs) is impeded by the growing memory demands of Key-Value (KV) cache, especially for longer sequences. Traditional KV cache eviction strategies, which discard less critical KV pairs based on…
Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding. This stems from the ''combinatorial contradiction'' phenomenon, where parallel tokens form…
Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…
The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…
Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency. However, its utility is limited by a fundamental…
Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the…