TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2410.00531/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTTPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices — HN submissionhttps://news.ycombinator.com/item?id=41730983urn:hackerpapers:submission:2410.00531:41730983Thu, 03 Oct 2024 14:11:20 GMT<p>Serving 70B-scale LLMs efficiently on low-resource edge devices [pdf]</p><p></p><p>248 points; 58 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2410.00531/">Paper and source history</a>. A submission is not an endorsement.</p>cs.DCTPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices — HN submissionhttps://news.ycombinator.com/item?id=41721761urn:hackerpapers:submission:2410.00531:41721761Wed, 02 Oct 2024 15:41:04 GMT<p>TPI-LLM: Serving 70B-Scale LLMs Efficiently on Low-Resource Edge Devices</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2410.00531/">Paper and source history</a>. A submission is not an endorsement.</p>cs.DC