https://hackerpaper.kaipfister.de/p/2512.10931/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=48510255urn:hackerpapers:mention:2512.10931:48510255Fri, 12 Jun 2026 22:44:48 GMT<p>AsyncResoning[1] does a trick of that sort to give agents concurrent cache views. You basically have two agents look at the same cache under different views. Say agent_0 gets [a_1, a_0] and agent_1 gets [a_0, a_1]. They also write to this cache concurrently while decoding. To solve positional embedding inconsistencies they rotate the query projections for each block (a_0 and a_1) separately. The computations you get that way do not exactly match the setup where you would naively prefill on every step, but are close enough. Same trick could be used for the setup discussed here, I guess…</p><p><a href="https://hackerpaper.kaipfister.de/p/2512.10931/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG