### 🔀 [#280](https://github.com/ikawrakow/ik_llama.cpp/pull/280) - Native build ooption for CUDA when GGML_NATIVE is set

| **Author** | `ikawrakow` |
| :--- | :--- |
| **State** | ❌ **Closed** |
| **Created** | 2025-03-22 |
| **Updated** | 2025-03-22 |

---

#### Description

Speeds up CUDA build time 3X