You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+20Lines changed: 20 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,3 +1,23 @@
1
+
### 0.43.1
2
+
3
+
#### Improvements and New Features:
4
+
5
+
- Improved the serialization format for 8-bit weights; this change is fully backwards compatible. (#1164, thanks to @younesbelkada for the contributions and @akx for the review).
6
+
- Added CUDA 12.4 support to the Linux x86-64 build workflow, expanding the library's compatibility with the latest CUDA versions. (#1171, kudos to @matthewdouglas for this addition).
7
+
- Docs enhancement: Improved the instructions for installing the library from source. (#1149, special thanks to @stevhliu for the enhancements).
8
+
9
+
#### Bug Fixes
10
+
11
+
- Fix 4bit quantization with blocksize = 4096, where an illegal memory access was encountered. (#1160, thanks @matthewdouglas for fixing and @YLGH for reporting)
0 commit comments