mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-05-03 04:41:47 +00:00
Add GitHub data: filename sanitization (#640)
This commit is contained in:
@@ -0,0 +1,13 @@
|
||||
### 🐛 [#137](https://github.com/ikawrakow/ik_llama.cpp/pull/137) - Fix AVX2 implementation of iq4_nl_r4
|
||||
|
||||
| **Author** | `ikawrakow` |
|
||||
| :--- | :--- |
|
||||
| **State** | ❌ **Closed** |
|
||||
| **Created** | 2024-12-11 |
|
||||
| **Updated** | 2024-12-11 |
|
||||
|
||||
---
|
||||
|
||||
#### Description
|
||||
|
||||
The implementation was using `_mm256_maddubs_epi16`, which overflows (and gets saturated) with the unsigned version of the non-linear quants `IQ4_NL` lookup table. This PR fixes it without a noticeable performance loss.
|
||||
Reference in New Issue
Block a user