From 50493d518a1b462b167ea5fed1901af7e229168d Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 11 Apr 2026 18:58:02 +0000 Subject: [PATCH] Upgrade llama.cpp from b8762 to b8763 - Updated GIT_TAG in CMakeLists.txt to b8763 - Updated README.md badge and link to b8763 - Updated CLAUDE.md version documentation to b8763 This release adds MERaLiON audio encoder support and CUDA flash attention optimizations. No breaking API changes - all C++ code remains compatible. https://claude.ai/code/session_01UuPBuVqDy8fNzgWtj2aPbk --- CLAUDE.md | 2 +- CMakeLists.txt | 2 +- README.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/CLAUDE.md b/CLAUDE.md index bdf6d036..30b67f6b 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -6,7 +6,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co Java bindings for [llama.cpp](https://github.com/ggerganov/llama.cpp) via JNI, providing a high-level API for LLM inference in Java. The Java layer communicates with a native C++ library through JNI. -Current llama.cpp pinned version: **b8762** +Current llama.cpp pinned version: **b8763** ## Upgrading CUDA Version diff --git a/CMakeLists.txt b/CMakeLists.txt index dfb0484a..e607db54 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -97,7 +97,7 @@ set(GGML_AVX512 OFF CACHE BOOL "" FORCE) FetchContent_Declare( llama.cpp GIT_REPOSITORY https://github.com/ggerganov/llama.cpp.git - GIT_TAG b8762 + GIT_TAG b8763 ) FetchContent_MakeAvailable(llama.cpp) diff --git a/README.md b/README.md index d982e055..41360a7e 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@ ![Java 8+](https://img.shields.io/badge/Java-8%2B-informational) -[![llama.cpp b8762](https://img.shields.io/badge/llama.cpp-%23b8762-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b8762) +[![llama.cpp b8763](https://img.shields.io/badge/llama.cpp-%23b8763-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b8763) # Java Bindings for [llama.cpp](https://github.com/ggerganov/llama.cpp)