mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-05-01 11:51:53 +00:00
21 lines
692 B
Markdown
21 lines
692 B
Markdown
### 🔀 [#497](https://github.com/ikawrakow/ik_llama.cpp/pull/497) - Make prompt cache saving and restoring MLA aware
|
|
|
|
| **Author** | `saood06` |
|
|
| :--- | :--- |
|
|
| **State** | ❌ **Closed** |
|
|
| **Created** | 2025-06-06 |
|
|
| **Updated** | 2025-06-06 |
|
|
|
|
---
|
|
|
|
#### Description
|
|
|
|
Tested working with both a long (3.5K tokens) and a short prompt with both matching up in size with what is expected. The long prompt was also tested on a fresh launch of the server to ensure it gave output consistent with what would be expected given the information in the prompt.
|
|
|
|
Closes #436
|
|
|
|
---
|
|
|
|
#### 💬 Conversation
|
|
|
|
👤 **ikawrakow** submitted a review the **2025-06-06** at **08:33:36**: ✅ `APPROVED` |