### 🔀 [#2](https://github.com/ikawrakow/ik_llama.cpp/pull/2) - Offload Bitnet token embeddings to the GPU - the right way

| **Author** | `ikawrakow` |
| :--- | :--- |
| **State** | ❌ **Closed** |
| **Created** | 2024-07-26 |
| **Updated** | 2024-07-26 |

---

#### Description

OK, I should have checked how it was done for Gemma and do the same for Bitnet. But better late than never.