# Hugging Face — Make your ZeroGPU Spaces go brrr with ahead-of-time compilation

- Company: Hugging Face (huggingface.co)
- Announced: 2025-09-02T00:00:00+00:00
- Category: capability-change
- Subject: Platform
- Models affected: FLUX.1-dev, Flux, Wan, LTX
- Source: https://huggingface.co/blog/zerogpu-aoti
- Record: https://forck.live/items/1630-make-your-zerogpu-spaces-go-brrr-with-ahead-of-time-compilation

Hugging Face announces support for PyTorch ahead-of-time (AoT) compilation in ZeroGPU Spaces, enabling faster model loading and inference with speedups of 1.3×–1.8× on models like Flux, Wan, and LTX.

## Evidence

Verbatim from https://huggingface.co/blog/zerogpu-aoti:

> In this post, we’ll show how to wire up Ahead-of-Time (AoT) compilation in ZeroGPU Spaces.

---

Record: https://forck.live/items/1630-make-your-zerogpu-spaces-go-brrr-with-ahead-of-time-compilation
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md