MeMPA: A Memory Mapped M-SIMD Co-Processor to Cope with the Memory Wall Issue(mdpi.com)32 points by PaulHoule 2 years ago | 3 comments
Multiword matrix multiplication over large finite fields in floating-point(arxiv.org)23 points by 7777777phil 9 months ago | 0 comments
QLoRA: Efficient Finetuning of Quantized LLMs(arxiv.org)270 points by Garcia98 3 years ago | 90 comments
BloombergGPT: A Large Language Model for Finance(arxiv.org)109 points by SerCe 3 years ago | 24 comments
Plimpton 322 is Babylonian exact sexagesimal trigonometry(sciencedirect.com)71 points by Luc 3 years ago | 5 comments