v0.40.13-rc1: llama.cpp: workaround Metal unary crash (#19372)
This temporary patch works around a regression on older versions of MacOS ggml_metal_library_compile_all: failed to build 'unary' library
What moved
This temporary patch works around a regression on older versions of MacOS ggml_metal_library_compile_all: failed to build 'unary' library
Why it matters
Filed as a public note from Ollama, 2026-10-28. The desk tags this brief LLM.
On the record
- Filed from the Ollama official GitHub releases feed on 2026-10-28.
- Primary source host: github.com.
- This temporary patch works around a regression on older versions of MacOS ggml_metal_library_compile_all: failed to build 'unary' library
Primary source
github.com
github.com
Desk
Logged as brief 190
Logged as brief 190
Cite this brief
v0.40.13-rc1: llama.cpp: workaround Metal unary crash (#19372) (Ollama, 2026-10-28) — https://labledgerdesk.pages.dev/b/2026/10/28/v0-40-13-rc1-llama-cpp-workaround-metal-unary-crash-19372/