b9769
📦 llama-cppView on GitHub →
🐛 1 fixes🔧 2 symbols
Summary
This release resolves a linking issue in ggml-vulkan when debug/test paths are enabled by ensuring ggml-cpu is linked correctly. It also provides numerous pre-built binaries for various operating systems and hardware configurations.
🐛 Bug Fixes
- Fixed linking failure when GGML_VULKAN_CHECK_RESULTS or RUN_TESTS are enabled by linking ggml-cpu, which contains the required symbol ggml_graph_compute_with_ctx().