### 🐛 [#105](https://github.com/ikawrakow/ik_llama.cpp/pull/105) - Fix quantized k-cache without FA

| **Author** | `ikawrakow` |
| :--- | :--- |
| **State** | ❌ **Closed** |
| **Created** | 2024-10-24 |
| **Updated** | 2024-10-24 |

---

#### Description

Ref  https://github.com/ggerganov/llama.cpp/pull/10032
Ref https://github.com/ggerganov/llama.cpp/pull/10021

Closes #103