Skip to content

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++

CI: build the Metal engine on macos-26 (#3870, #3824)

stuchapin9096c09a1929c74
diff --git a/.github/workflows/metal-build.yml b/.github/workflows/metal-build.yml
index 7a69696fc..a4f7d9970 100644
--- a/.github/workflows/metal-build.yml
+++ b/.github/workflows/metal-build.yml
@@ -20,7 +20,9 @@ permissions:
jobs:
metal-link:
- runs-on: macos-14
+ # the macOS 26 SDK: metal/src/mtl_rt.mm names MTLGPUFamilyMetal4 (and MTLCompileOptions.mathMode, macOS 15) behind @available,
+ # which is a run-time check; the names must still be in the SDK the engine is compiled against
+ runs-on: macos-26
timeout-minutes: 45
env:
# setup.py's LLAMA_CPP_COMMIT and metal/setup_mac.py's metal-cpp pin