Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2505.21411/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTPangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity — HN submissionhttps://news.ycombinator.com/item?id=44441089urn:hackerpapers:submission:2505.21411:44441089Wed, 02 Jul 2025 07:36:41 GMT<p>Huawei releases an open weight model trained on Huawei Ascend GPUs</p><p></p><p>321 points; 333 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2505.21411/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CLPangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity — HN submissionhttps://news.ycombinator.com/item?id=44438457urn:hackerpapers:submission:2505.21411:44438457Tue, 01 Jul 2025 22:17:27 GMT<p>Pangu Pro Moe: Mixture of Grouped Experts for Efficient Sparsity</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2505.21411/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL