M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2504.10449/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTM1: Towards Scalable Test-Time Compute with Mamba Reasoning Models — mentioned by cubefoxhttps://news.ycombinator.com/item?id=43838433urn:hackerpapers:mention:2504.10449:43838433Tue, 29 Apr 2025 21:48:39 GMT<p>Another recent transformer/SSM hybrid is &quot;M1&quot;, with a more than 3x claimed inference speed-up compared to equivalent transformers: https://arxiv.org/pdf/2504.10449 IBM is claiming at least a 2x inference speed-up with Bamba. Both groups say that future SSM optimizations to vLLM would lead to further inference speed improvement.</p><p><a href="https://hackerpaper.kaipfister.de/p/2504.10449/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGM1: Towards Scalable Test-Time Compute with Mamba Reasoning Models — HN submissionhttps://news.ycombinator.com/item?id=43695562urn:hackerpapers:submission:2504.10449:43695562Tue, 15 Apr 2025 17:00:18 GMT<p>M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models</p><p></p><p>33 points; 3 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2504.10449/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG