ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-05-03 04:41:47 +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

23
github-data/pull_requests/528-Fix bug introduced in #524_#525.md Normal file
View File

@@ -0,0 +1,23 @@
### 🐛 [#528](https://github.com/ikawrakow/ik_llama.cpp/pull/528) - Fix bug introduced in [#524](https://github.com/ikawrakow/ik_llama.cpp/issues/524)/[#525](https://github.com/ikawrakow/ik_llama.cpp/issues/525)
| **Author** | `ikawrakow` |
| :--- | :--- |
| **State** | ❌ **Closed** |
| **Created** | 2025-06-14 |
| **Updated** | 2025-06-14 |
---
#### Description
When adding the faster GEMM in #524 / #525 I forgot to add the call to `iqk_convert_repack` also in the MoE matrix multiplication functions, which causes a crash (see #527). This PR fixes it.
---
#### 💬 Conversation
👤 **ycat3** commented the **2025-06-14** at **10:30:08**:<br>
Thanks.
It works fine.
#527