v0.40.7-rc1: mlx: deduplicate CUDA runtime payloads (#17956)
- Ollama: 85 events in the last 90 days
- Ollama: 79th Release in the last 90 days
- Previous: 2 days earlier · v0.40.7-rc0: mlx: add PPLX Decider v1.2 support (#19072)
What happened
Deduplicate MLX CUDA runtime payloads Move CUDA libraries shared by the GGML and MLX backends into the sibling CUDA payload, and teach in-process and subprocess MLX loading to resolve that packaged dependency directory. Keep MLX-private libraries and JIT headers in the MLX overlay, include the full OpenBLAS Fortran runtime closure, and verify those dependencies in release packaging. address comments
Summary assembled by rule from the sources below
Why it's spreading
Sources
Release
- v0.40.7-rc1: mlx: deduplicate CUDA runtime payloads (#17956)Ollama Releases