cd/entity/Nano-vLLM· home› entities› Nano-vLLM
grep -l @nano-vllm /news/*.json | wc -l → 1

Nano-vLLM

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

04:00
2026-08-28
arxiv.org
artificial-intelligence

Affix Cache for Diffusion Large Language Models

Researchers introduced ACache, an affix-oriented cache reuse mechanism for Diffusion Large Language Models (DLLMs) that selectively recomputes key-value states of critical Anchor Tokens to maintain ac…

// co-occurs with top 3 entities
ACache 1 Fast-dLLM 1 Diffusion Large Language Models 1
// topics top 4 topics
artificial intelligence 1 large language models 1 ai research 1 ai infrastructure 1