From f0bf326a9afcac3f2a61ff0dcdf01164999df1aa Mon Sep 17 00:00:00 2001 From: Andrei Date: Sun, 28 Jun 2026 16:07:43 -0700 Subject: [PATCH] feat: update llama.cpp to b3fed31b9 (#2322) * feat: update llama.cpp to fdbd6abee * feat: update llama.cpp to b3fed31b9 --- CHANGELOG.md | 2 +- vendor/llama.cpp | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 2659bac3f..9a7abb40f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,7 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ## [Unreleased] - feat(example): support chained NextN heads for server MTP drafting -- feat: update llama.cpp to ggml-org/llama.cpp@92e854ab8 +- feat: update llama.cpp to ggml-org/llama.cpp@b3fed31b9 - fix: preserve recurrent/hybrid model state when the full prompt is already cached by @allthatido and @abetlen in #2306 ## [0.3.31] diff --git a/vendor/llama.cpp b/vendor/llama.cpp index 92e854ab8..b3fed31b9 160000 --- a/vendor/llama.cpp +++ b/vendor/llama.cpp @@ -1 +1 @@ -Subproject commit 92e854ab836254bb7f2eb49babd5613474bdb700 +Subproject commit b3fed31b99f9bd37725833674252bccb429bb183