1
VoltanaLLM: Energy-Efficient LLM Serving
LLM服务节能新方案：利用预填充/解码解耦架构，动态GPU频率控制实现36.3%能耗节省
Article URL: https://supercomputing-system-ai-lab.github.io/projects/voltana/ Comments URL: https://news.ycombinator.com/item?id=48655520 Points: 2 # …
2
Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models
提出预测预填充方法，让扩散语言模型高效处理超长上下文，解码速度显著提升。
arXiv:2606.10537v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing r…
3
Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
无需重写整个输出，LLM编辑效率新突破：Copy-as-Decode用语法约束并行预填充，大幅加速文本代码编辑。
arXiv:2604.18170v2 Announce Type: replace-cross Abstract: LLMs edit text and code by autoregressively regenerating the full output, even when most tok…
4
Prism: Spectral-Aware Block-Sparse Attention
光谱感知的块稀疏注意力机制，突破长上下文LLM预填充效率瓶颈
arXiv:2602.08426v2 Announce Type: replace-cross Abstract: Block-sparse attention is promising for accelerating long-context LLM pre-filling, yet ident…
5
PreFT: Prefill-only finetuning for efficient inference
新微调方法PreFT仅优化预填充阶段，解决大模型个性化服务时PEFT导致的吞吐量瓶颈，理论与实证兼备。
arXiv:2605.14217v1 Announce Type: cross Abstract: Large language models can now be personalised efficiently at scale using parameter efficient finetun…