Related papers: BlockBatch: Multi-Scale Consensus Decoding for Eff…

Discrete diffusion language models (dLLMs) provide a fast and flexible alternative to autoregressive models (ARMs) via iterative denoising with parallel updates. However, their evaluation is challenging: existing metrics conflate denoiser…

Speculative decoding accelerates large language model inference by proposing tokens with a lightweight draft model and selectively accepting them using a target model. This work introduces DropMatch, a novel approach that matches draft…

Recently, Diffusion Large Language Models (DLLMs) have offered high throughput and effective sequential reasoning, making them a competitive alternative to autoregressive LLMs (ALLMs). However, parallel decoding, which enables simultaneous…

Block diffusion LLMs are emerging as a promising next paradigm for language generation, but their use of KV caching makes memory access a dominant bottleneck in long-context settings. While dynamic sparse attention has been actively…

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…

Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation…

Large Language Models (LLMs) for complex reasoning is often hindered by high computational costs and latency, while resource-efficient Small Language Models (SLMs) typically lack the necessary reasoning capacity. Existing collaborative…

Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…

Speculative decoding is an emerging technique that accelerates large language model (LLM) inference by allowing a smaller draft model to predict multiple tokens in advance, which are then verified or corrected by a larger target model. In…

Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the…

Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs'…

Diffusion Language Models (DLMs) enable fast generation, yet training large DLMs from scratch is costly. As a practical shortcut, adapting off-the-shelf Auto-Regressive (AR) model weights into a DLM could quickly equip the DLM with strong…

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges.…

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive models, primarily due to their ability to enable parallel decoding. Despite this advantage, most existing DLMs rely on a fixed generation…

Diffusion Large Language Models (dLLMs) have demonstrated significant potential for high-speed inference. However, current confidence-driven decoding strategies are constrained by limited parallelism, typically achieving only 1--3 tokens…

We introduce the Block Transformer which adopts hierarchical global-to-local modeling to autoregressive transformers to mitigate the inference bottlenecks associated with self-attention. Self-attention requires the key-value (KV) cache of…

Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accuracy at the cost of multi-step autoregressive inference,…

As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation…