Оригинальная аннотация: High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rather than compute-bound: each decoding step must stream the accumulated key/value (KV) cache from memory, so bandwidth demand grows with context length while only one token is emitted. Two parallel approaches have therefore emerged: reducing memory access with efficient attention variants and linear-time mixers such as Mamba, or increasing parallel computation by generating blocks of tokens at once. However, technical challenges arise when combini
Полезно для: Не указано · Ограничение: Не указано
2026-06-17T18:10:23+00:00 · Длинный контекст, Рассуждения · Источник
Оригинальная аннотация: Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks. Recently, Diffusion Language Models (DLMs) have emerged as an alternative paradigm that generates text through iterative denoising rather than next-token prediction, allowing parallel refinement of entire sequences. While numerous diffusion-based architectures have been proposed, differences in evaluation protocols, datasets, inference budgets, and generation hyperparameters make it difficult to compare their capabilities and understand
Полезно для: Не указано · Ограничение: Не указано
2026-06-17T18:10:23+00:00 · Длинный контекст, Рассуждения · Источник
Оригинальная аннотация: Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks. Recently, Diffusion Language Models (DLMs) have emerged as an alternative paradigm that generates text through iterative denoising rather than next-token prediction, allowing parallel refinement of entire sequences. While numerous diffusion-based architectures have been proposed, differences in evaluation protocols, datasets, inference budgets, and generation hyperparameters make it difficult to compare their capabilities and understand
Полезно для: Не указано · Ограничение: Не указано
2026-06-09T08:06:22+00:00 · Ускорение инференса, Длинный контекст · Источник
Оригинальная аннотация: Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with context length and becomes prohibitive for long-context scenarios. We propose Prefilling-dLLM, a training-free prefill-decode disaggregation framework for dLLMs that partitions the prefix into N chunks, caches their KV representations once, and selects the top-K most relevant chunks with intra-chunk token sparsity for decoding, showing that sparse prefilling can outperform dense attention while reducing per-step complexity from quadratic in t
Полезно для: Не указано · Ограничение: Не указано
2026-05-20T07:06:54Z · Ускорение инференса, Длинный контекст · Источник
Оригинальная аннотация: Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of the denoising process without KV cache. Recent sparse attention methods for dLLMs mitigate this cost via block-sparse computation, which is applied only in later iterations when model performance is less sensitive to coarse-grained sparse approximation, but yields limited improvements in computational efficiency and acceleration. This motivates a finer-grained sparsification strategy that can be applied from earlier iterations and leverages reusa
Оригинальная аннотация: Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus primarily on autoregressive architectures. This study investigates whether prompt compression transfers effectively to diffusion large language models (DLLMs) using LLMLingua-2, specifically the 8B-parameter DLLM LLaDA. We evaluate compression performance on GSM8K, DUC2004, and ShareGPT using 250 prompts per dataset at an approximate 2$\times$ compression ratio, across mathematical reasoning, prompt reconstruction, and summarization tasks. Outputs generated from original prompts,