Daniel HiltgenandGitHub 2cd63f7a15 mlx: deduplicate CUDA runtime payloads (#17956) ...

* 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

2026-10-20 14:15:15 -07:00

..

support

app: add code for macOS and Windows apps under 'app' (#12933)

2025-11-04 11:40:17 -08:00

.this-is-the-create-dmg-repo

app: add code for macOS and Windows apps under 'app' (#12933)

2025-11-04 11:40:17 -08:00

build_darwin.sh

build: go deps (#18161)

2026-09-01 12:59:48 -07:00

build_docker.sh

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

build_linux.sh

mlx: deduplicate CUDA runtime payloads (#17956)

2026-10-20 14:15:15 -07:00

build_windows.ps1

mlx: deduplicate CUDA runtime payloads (#17956)

2026-10-20 14:15:15 -07:00

buildkitd.toml.example

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

create-dmg.sh

app: add code for macOS and Windows apps under 'app' (#12933)

2025-11-04 11:40:17 -08:00

env.sh

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

install.ps1

win: progress reporting on install download (#14219)

2026-02-12 12:06:56 -08:00

install.sh

install: prevent partial download script execution (#14311)

2026-02-18 18:32:45 -08:00

push_docker.sh

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)

2026-05-29 13:35:47 -07:00

tag_latest.sh

CI: clean up naming, fix tagging latest (#6832)

2024-09-16 16:18:41 -07:00