{"slug":"from-cuda-to-mlx-how-k-search-brings-decades-of-200f39cc","url":"https://silinex.xyz/wire/from-cuda-to-mlx-how-k-search-brings-decades-of-200f39cc","json_url":"https://silinex.xyz/wire/from-cuda-to-mlx-how-k-search-brings-decades-of-200f39cc.json","md_url":"https://silinex.xyz/wire/from-cuda-to-mlx-how-k-search-brings-decades-of-200f39cc.md","headline":"From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon","headline_zh":"从CUDA到MLX：K-Search如何将数十年的内核专业经验带到Apple Silicon","title":"From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon","summary":"According to public reporting via BAIR Blog, figure 1: CUDA-to-MLX optimization translation map.","summary_zh":"据BAIR Blog的公开报道，图1：CUDA到MLX优化转换映射图。","date_published":"2026-07-29T09:00:00.000+00:00","date_modified":"2026-11-12T06:30:33.138+00:00","author":{"type":"Organization","name":"BAIR Blog","url":"http://bair.berkeley.edu/blog/2026/07/29/cuda-to-mlx-k-search/"},"publisher":{"name":"Silicon Nexus","url":"https://silinex.xyz/"},"category":"chips","language":"en","source_url":"http://bair.berkeley.edu/blog/2026/07/29/cuda-to-mlx-k-search/","source_name":"BAIR Blog","key_facts":["figure 1: CUDA-to-MLX optimization translation map.","Figure 1: CUDA-to-MLX optimization translation map.","CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction.","We face a new epoch in computing."],"key_facts_zh":["图1：CUDA到MLX的优化转换映射。","图1：CUDA到MLX的优化转换映射。","CUDA优化知识可以转化为架构原生的MLX策略，而非逐条指令照搬。","我们正迎来计算的新纪元。"],"body_md":"## Wire brief\n\nAccording to public reporting via BAIR Blog, figure 1: CUDA-to-MLX optimization translation map.\n\nIn related context, cUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction. We face a new epoch in computing. Hardware is changing rapidly — not just faster GPUs, but a growing range of chips from different vendors, each with its own architecture and often tailored to specific AI workloads.\n\nReporting also notes that software is changing just as fast, and AI coding tools now generate in minutes what took months of effort a few years ago. With so much of computing now centered on AI, GPU kernels are a crucial component of its success. These are the low-level programs that run inside the GPU, and writing efficient ones is far from obvious — it takes years of expertise to get right. Transferring a kernel from one vendor’s hardware to another is harder still, and often means rediscovering the same optimizations from scratch.\n\nThis Silicon News Wire item is a paraphrased brief for readability; full wording and context remain on the origin page.\n\n## Source & notice\n\nThis Silicon News Wire brief paraphrases public reporting from **BAIR Blog** for carbon readers and silicon citation. **It is not a verbatim full-text reprint.**\n\nRead the original: [From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon](http://bair.berkeley.edu/blog/2026/07/29/cuda-to-mlx-k-search/)\n","body_md_zh":"## 电讯正文\n\n据BAIR Blog的公开报道，图1：CUDA到MLX优化转换映射图。\n\n在相关背景下，CUDA优化知识可以被转化为架构原生的MLX策略，而不是逐条指令地照搬。我们正面临计算领域的新时代。硬件正在快速变化——不仅是更快的GPU，还有来自不同厂商的日益增多的芯片，每一款都有其自身的架构，且往往针对特定的AI工作负载量身定制。\n\n报道还指出，软件的变化同样迅速，AI编码工具如今能在几分钟内生成几年前需要数月努力才能完成的内容。由于当前计算领域大量围绕AI展开，GPU内核是其成功的关键组成部分。这些是在GPU内部运行的低层程序，编写高效的内核绝非易事——需要多年的专业经验才能做好。将内核从一个厂商的硬件迁移到另一个厂商的硬件则更加困难，往往意味着要从头重新发现相同的优化方法。\n\n## 来源与声明\n\n本电讯由 Silicon News Wire 依据 **BAIR Blog** 公开报道做要点改写与润色，便于碳基阅读与硅基引用；**不是原文全文转载**。\n\n阅读原文：[从CUDA到MLX：K-Search如何将数十年的内核专业经验带到Apple Silicon](http://bair.berkeley.edu/blog/2026/07/29/cuda-to-mlx-k-search/)\n","observations":{"human":3,"bot":7,"crawlers":[{"crawlerId":"AhrefsBot","hits":3,"lastSeenAt":"2026-11-11T04:43:05.862Z"},{"crawlerId":"Amazonbot","hits":2,"lastSeenAt":"2026-11-12T11:15:17.617Z"},{"crawlerId":"ClaudeBot","hits":2,"lastSeenAt":"2026-11-12T12:57:47.048Z"}],"last_seen_at":"2026-11-12T12:57:47.048Z","note":"Counts are request logs classified by User-Agent. User-Agents can be spoofed. This is not proof of search-engine or LLM inclusion."}}