We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 4ff48f0 commit f0bf326Copy full SHA for f0bf326
2 files changed
CHANGELOG.md
@@ -8,7 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
8
## [Unreleased]
9
10
- feat(example): support chained NextN heads for server MTP drafting
11
-- feat: update llama.cpp to ggml-org/llama.cpp@92e854ab8
+- feat: update llama.cpp to ggml-org/llama.cpp@b3fed31b9
12
- fix: preserve recurrent/hybrid model state when the full prompt is already cached by @allthatido and @abetlen in #2306
13
14
## [0.3.31]
vendor/llama.cpp
0 commit comments