OpenBLAS

Latest news

1. 21 Oct
   Ollama v0.40.7-rc1 deduplicates CUDA runtime payloads in MLX and GGML backends

   Ollama's v0.40.7-rc1 release moves shared CUDA libraries used by the GGML and MLX backends into a sibling CUDA payload and updates MLX loading to resolve that packaged dependency. The release also keeps MLX-private libraries and JIT headers in the MLX overlay, includes the full OpenBLAS Fortran runtime closure, and verifies those dependencies in release packaging.

   Developers · 1 source

Articles

No articles about OpenBLAS yet.