LLM inference in C/C++
C++ ggml
ci : update macos release to use macos-26 runner (#23878)
Georgi Gerganovdc71236b6c89
diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex c3a018425e..08f02af63e 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -66,7 +66,7 @@ jobs:include:- build: 'arm64'arch: 'arm64'- os: macos-14+ os: macos-26defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON"# TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23780)# in order to enable it again, we have to provision dedicated runners to run it@@ -1134,7 +1134,7 @@ jobs:ios-xcode-build:needs: [check_release]if: ${{ needs.check_release.outputs.should_release == 'true' }}- runs-on: macos-15+ runs-on: macos-26steps:- name: Checkout code