https://hackerpaper.kaipfister.de/p/2512.23236/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMThttps://news.ycombinator.com/item?id=46527970urn:hackerpapers:submission:2512.23236:46527970Wed, 07 Jan 2026 16:03:39 GMT<p>KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2512.23236/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGhttps://news.ycombinator.com/item?id=46442841urn:hackerpapers:submission:2512.23236:46442841Wed, 31 Dec 2025 09:59:15 GMT<p>KernelEvolve: Agentic kernel coding for heterogeneous AI accelerators (Meta)</p><p>We’re sharing KernelEvolve, an agentic system we built at Meta to automatically generate and evolve high-performance kernels across heterogeneous AI accelerators. The core motivation is that modern AI stacks increasingly depend on hand-optimized kernels (GEMM, attention, reductions, fused ops), but writing and tuning them for each hardware target (NVIDIA GPUs, AMD GPUs, custom accelerators like MTIA) does not scale. KernelEvolve treats kernel programming as a search + evolution problem: • An LLM generates candidate kernels (e.g., Triton-like code) • Kernels are compiled, benchmarked, and…</p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2512.23236/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG