
Luminal
Luminal is a YC Summer 2025 (S25) company. Team of 3.
About Luminal
Summary
Luminal builds a compiler and inference OS for AI models, targeting developers and teams running large-scale model inference. It compiles PyTorch and Hugging Face models ahead of time into optimized GPU and ASIC kernels, replacing interpreted runtime engines with generated native code. The stack covers the full pipeline from graph IR through hardware-aware optimization to codegen, then dynamically schedules and load-balances workloads across heterogeneous compute clusters to maximize throughput and reduce idle GPU cost.
Go-to-market
ML engineers and infrastructure teams adopt Luminal to replace existing inference engines; the GitHub repository and Discord server point to a developer-led, self-serve adoption path.
From the Y Combinator listing
Making AI run fast on any hardware.
Luminal builds an ML framework and compiler that generates GPU code. Our stack 10x's model speed while simplifying deployment and cutting idle GPU costs Github: https://github.com/luminal-ai/luminal Discord: https://discord.gg/APjuwHAbGy
Facts
- B2B / B2B -> Infrastructure
- 3
- Active
- Early
Founders (3)
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works