# Makora uses LLMs to write high-performance， low-level GPU code. But the real play is treating codege…

- 来源：SemiAnalysis (@SemiAnalysis_)
- 发布时间：2026-04-16 12:00
- AIHOT 链接：https://aihot.virxact.com/items/cmo0ym46d037lsli2yy5qv419
- 原文链接：https://x.com/SemiAnalysis_/status/2044626979127783746

## AI 摘要

Makora 使用 LLMs 编写高性能、低层级的 GPU 代码。但真正的策略是将 codegen 视为顺风。假设模型持续进步，然后围绕这一点构建整个平台。https://t.co/0J2TIBIYZR

## 正文

Makora uses LLMs to write high-performance， low-level GPU code. But the real play is treating codegen as a tailwind. Assume the models keep getting better， then build the entire platform around that.