Files
LocalAI/.github/workflows
Ettore Di Giacinto 017bdee4e4 ci(vllm): install libnuma1 + libgomp1 on bigger-runner
The vllm 0.14.1+cpu wheel ships a _C C++ extension that dlopens
libnuma.so.1 at import time. When the runner host doesn't have it,
the extension silently fails to register its torch ops, so
EngineCore crashes on init_device with:

  AttributeError: '_OpNamespace' '_C_utils' object has no attribute
    'init_cpu_threads_env'

Also add libgomp1 (OpenMP runtime, used by torch CPU kernels) to be
safe on stripped-down runners.
2026-04-12 20:18:13 +00:00
..
2026-03-02 14:48:00 +01:00
2026-03-14 17:49:36 +01:00
2026-04-12 08:51:30 +02:00
2026-04-12 08:51:30 +02:00
2026-03-30 00:47:27 +02:00