{"type": "article", "title": "Accelerating Block Low-Rank Foundation Model Inference on MemoryConstrained GPUs", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/accelerating-block-low-rank-foundation-model-inference-on-memoryconstrained-gpus", "original_source": "https://dl.acm.org/doi/full/10.1145/3806645.3807580", "published": "2026-07-16T02:44:35+00:00", "accessed": "2026-07-16", "id": "accelerating-block-low-rank-foundation-model-inference-on-memoryconstrained-gpus"}