https://hackerpaper.kaipfister.de/p/2509.02510/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=48990705urn:hackerpapers:mention:2509.02510:48990705Tue, 21 Jul 2026 11:09:03 GMT<p>Switching to mlx-vlm is basically harmful since it (like vllm and sglang) have such garbage support for modern samplers. To be clear, I am one of the authors on the min_p paper, and if min_p is the best you have (when llamacpp supports the far superior top-n-sigma), than I have no reason to switch even if you are somehow faster. (https://arxiv.org/abs/2411.07641) And if you do care to support modern samplers, you can start with the following: 1. https://arxiv.org/abs/2509.23234 2. https://arxiv.org/abs/2509.02510 3. https://arxiv.org/abs/2604.11012</p><p><a href="https://hackerpaper.kaipfister.de/p/2509.02510/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL