[{"data":1,"prerenderedAt":35},["ShallowReactive",2],{"chapter:teenygrad\u002Fappendix\u002Ffaq-and-roadmap.json":3},{"project":4,"route":5,"title":6,"titleHtml":7,"navTitle":6,"part":8,"sourcePath":9,"editUrl":10,"html":11,"toc":12,"hasMermaid":30,"prev":31,"next":34},"teenygrad","\u002Fteenygrad\u002Fappendix\u002Ffaq-and-roadmap","FAQ & Roadmap","FAQ & Roadmap","Appendix","appendix\u002Ffaq-and-roadmap.md","https:\u002F\u002Fgithub.com\u002Fteenygrad\u002Fteenygrad\u002Fedit\u002Fmain\u002Fbooks\u002Fteenygrad\u002Fsrc\u002Fappendix\u002Ffaq-and-roadmap.md","\u003Ch2 id=\"roadmap\">Roadmap\u003C\u002Fh2>\n\u003Ch3 id=\"2026-q1--torch-inductor-in-rust\">2026 Q1 — Torch Inductor in Rust\u003C\u002Fh3>\n\u003Cul>\n\u003Cli>\u003Cstrong>2026 and beyond\u003C\u002Fstrong>\n\u003Cul>\n\u003Cli>Q3: \u003Ccode>teeny-llm\u003C\u002Fcode> — vLLM-style inference, 2x faster\u003C\u002Fli>\n\u003Cli>Q4: performance optimization\u003C\u002Fli>\n\u003C\u002Ful>\n\u003C\u002Fli>\n\u003Cli>\u003Cstrong>2027 and beyond\u003C\u002Fstrong>\n\u003Cul>\n\u003Cli>Q2: embedded support\u003C\u002Fli>\n\u003Cli>Q3: sparsity\u002Fquantization support\u003C\u002Fli>\n\u003Cli>Q4: observability\u002Fmetrics\u003C\u002Fli>\n\u003C\u002Ful>\n\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>(See the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fteenygrad\u002Fteenygrad#roadmap\" target=\"_blank\" rel=\"noopener noreferrer\">repository README\u003C\u002Fa> for the current,\nauthoritative roadmap — this chapter may lag behind.)\u003C\u002Fp>\n\u003Ch2 id=\"faq\">FAQ\u003C\u002Fh2>\n\u003Ch3 id=\"why-create-this-project-when-pytorch-tensorflow-and-tinygrad-already-exist\">Why create this project when PyTorch, TensorFlow, and tinygrad already exist?\u003C\u002Fh3>\n\u003Cp>Those frameworks excel at development and deployment on large-scale infrastructure. We believe\nthe future of AI lies in devices of all sizes — from edge devices to massive clusters. Existing\nframeworks are relatively heavy; TensorFlow Lite comes closest to this vision, but a modern,\nmemory-safe language was preferred over C.\u003C\u002Fp>\n\u003Cp>At the same time, we didn’t want to sacrifice distributed training or other advanced features\noffered by larger projects — hence teenygrad: a lightweight but powerful alternative.\u003C\u002Fp>\n\u003Ch3 id=\"im-interested-in-contributing--how-do-i-get-started\">I’m interested in contributing — how do I get started?\u003C\u002Fh3>\n\u003Cp>See \u003Ca href=\"\u002Fteenygrad\u002Fcontributing\u002Fcontributing\">Contributing to Teenygrad\u003C\u002Fa>.\u003C\u002Fp>\n",[13,17,21,24,27],{"id":14,"text":15,"level":16},"roadmap","Roadmap",2,{"id":18,"text":19,"level":20},"2026-q1--torch-inductor-in-rust","2026 Q1 — Torch Inductor in Rust",3,{"id":22,"text":23,"level":16},"faq","FAQ",{"id":25,"text":26,"level":20},"why-create-this-project-when-pytorch-tensorflow-and-tinygrad-already-exist","Why create this project when PyTorch, TensorFlow, and tinygrad already exist?",{"id":28,"text":29,"level":20},"im-interested-in-contributing--how-do-i-get-started","I’m interested in contributing — how do I get started?",false,{"title":32,"titleHtml":32,"route":33},"Contributing to Teenygrad","\u002Fteenygrad\u002Fcontributing\u002Fcontributing",null,1786271829572]