We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent f0bf326 commit 2bc11acCopy full SHA for 2bc11ac
2 files changed
CHANGELOG.md
@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
7
8
## [Unreleased]
9
10
+## [0.3.32]
11
+
12
- feat(example): support chained NextN heads for server MTP drafting
13
- feat: update llama.cpp to ggml-org/llama.cpp@b3fed31b9
14
- fix: preserve recurrent/hybrid model state when the full prompt is already cached by @allthatido and @abetlen in #2306
llama_cpp/__init__.py
@@ -1,4 +1,4 @@
1
from .llama_cpp import *
2
from .llama import *
3
4
-__version__ = "0.3.31"
+__version__ = "0.3.32"
0 commit comments