4 papers
DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs
Lizhuo Luo, Shenggui Li, Yonggang Wen +1
Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block…
DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
Lizhuo Luo, Zhuoran Shi, Jiajun Luo +4
Diffusion large language models (dLLMs) have shown advantages in text generation, particularly due to their inherent ability for parallel decoding. However, constrained by the qual…
FlowSpec: Continuous Pipelined Speculative Decoding for Efficient Distributed LLM Inference
Xing Liu, Lizhuo Luo, Ming Tang +2
Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple…
Staleness-Centric Optimizations for Parallel Diffusion MoE Inference
Jiajun Luo, Lizhuo Luo, Jianru Xu +4
Mixture-of-Experts-based (MoE-based) diffusion models demonstrate remarkable scalability in high-fidelity image generation, yet their reliance on expert parallelism introduces crit…