← Back to all news
arXiv AI By Wenjie Huang, Jun Zhang, Hongyaoxing Gu, Haoyang Huang, Tianqi Xu, Xinyue Hao, Xinyi Hu, Xinle Du, Jun Dai, Shuang Ge, Chen Lei, Yue Li, Mingcheng Wan

Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference

Read the original on arXiv AI →

Raincheck is a framework that defers multimodal prefill for large language models, allowing initial token selection to be decoupled from later information needs. It preserves unselected tokens and progressively prefills them during decoding, using unused compute capacity and scheduling gaps. Experiments on Qwen3-VL-8B and Qwen3.5-9B show that Raincheck recovers a significant portion of quality lost to hard pruning and reduces first-turn time-to-first-token by up to 24.1% with minimal impact on token generation speed.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 28

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models

arXiv:2607. 22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens.

By Jinsong Shu, Chenyang Wu, Zhongle Xie, Baokun Wang, Lidan Shou
llmsefficiencymultimodalbenchmarks
More like this →
arXiv Computation and Language
Sep 1

Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models

arXiv:2606.10537v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with...

By Jing Xiong, Qi Han, Shansan Gong, Yunta Hsieh, Boyuan Zheng, Chengyue Wu, Chaofan Tao, Chenyang Zhao, Ngai Wong
llmsdiffusionefficiencybenchmarks
More like this →
Hugging Face Trending Papers
Jul 2

PARTREP: Learning What to Repeat for Decoder-only LLMs

While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones. A simple and effective remedy is prompt repetition -- just appending a second copy of prompt before generation can redistribute grounding across positions and improve reasoning performance.

llmsefficiencybenchmarks
More like this →