ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-05-03 12:51:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add GitHub data (#637)

Browse Source
This commit is contained in:
Thomas
2025-07-22 18:18:40 +02:00
committed by GitHub
parent 866c70e60d
commit ab7d193fe0
626 changed files with 175142 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
github-data/pull_requests/391-Fix DeepSeek q8_0 cache.md Normal file
View File

@@ -0,0 +1,17 @@
### 🐛 [#391](https://github.com/ikawrakow/ik_llama.cpp/pull/391) - Fix DeepSeek q8_0 cache
| **Author** | `ikawrakow` |
| :--- | :--- |
| **State** | ❌ **Closed** |
| **Created** | 2025-05-07 |
| **Updated** | 2025-05-07 |
---
#### Description
Nobody has used `ik_llama.cpp` with a DeepSeek model and `Q8_0` KV cache since PR #351?
This PR fixes the assert one gets when one tries to use a DeepSeek model on the CPU using `Q8_0` KV cache.
Also, it seems the optimization I added in #351 to repack the `K` cache to `Q8_0_R8` seems to lower TG performance for DeepSeek models, so disabling it.