Fast-dLLM: Training-Free Acceleration Method for Diffusion Language Models Using KV Cache and Parallel Decoding
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of…
Read the full articleYou might also wanna read
Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices
arXiv:2607.08786v1 Announce Type: new Abstract: With the growing deployment of large language models (LLMs), LLM inference cost has become a
LK Losses: A New Training Objective to Optimize Acceptance Rate in Speculative Decoding for LLMs
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate
arxiv.org·1mo agoBlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving
arXiv:2607.08930v1 Announce Type: new Abstract: Efficient serving of diffusion large language models (dLLMs) is hindered by convergence hete
SemDLM+: Improving Diffusion Language Models by Balancing Bias and Variance in Transition Kernel Design
Diffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models. However, their
arxiv.org·1mo ago
RTP-LLM: Alibaba's High-Performance Inference Engine for Large Language Model Deployment
Large Language Models (LLMs) have revolutionized AI applications, but deploying them at scale presents significant challenges. We present RT
arxiv.org·1mo ago
iLLaDA: An 8B Masked Diffusion Language Model Trained with Bidirectional Attention
Modern large language models are predominantly trained with autoregressive factorization and causal attention. We present \emph{iLLaDA}, an
arxiv.org·21d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.