mirror of
https://github.com/ollama/ollama.git
synced 2026-07-05 23:31:01 +00:00
570679c9e0
Bump MLX to the latest selected upstream ref and update the MLX/imagegen wrappers and tests for the new API behavior. Fix the CUDA MLX archive so runtime NVRTC kernels work after deployment: package CUTE/CUTLASS headers, include the CUDA runtime header closure, and stage a coherent CUDA-toolkit-matched CCCL tree instead of MLX's fetched CCCL for CUDA payloads. The previous archive could build successfully but crash at runtime due to missing or incompatible JIT headers. |
||
|---|---|---|
| .. | ||
| support | ||
| .this-is-the-create-dmg-repo | ||
| build_darwin.sh | ||
| build_docker.sh | ||
| build_linux.sh | ||
| build_windows.ps1 | ||
| buildkitd.toml.example | ||
| create-dmg.sh | ||
| deduplicate_cuda_libs.sh | ||
| env.sh | ||
| install.ps1 | ||
| install.sh | ||
| push_docker.sh | ||
| tag_latest.sh | ||