Daniel Hiltgen 0c3d0e7533 build: avoid unbounded parallel builds (#12319) ...

With the addition of cuda v13, on a clean setup, the level of parallelism
was causing docker desktop to become overwhelmed and compilers
were crashing.  This limits to 8 parallel per build stage, with the ability
to override if you have many more cores available.

2025-09-18 14:57:01 -07:00

..

build_darwin.sh

Align versions for local builds (#9635)

2025-03-14 15:44:08 -07:00

build_docker.sh

Update ROCm (6.3 linux, 6.2 windows) and CUDA v12.8 (#9304)

2025-02-25 13:47:36 -08:00

build_linux.sh

Update ROCm (6.3 linux, 6.2 windows) and CUDA v12.8 (#9304)

2025-02-25 13:47:36 -08:00

build_windows.ps1

Add v12 + v13 cuda support (#12000)

2025-09-10 12:05:18 -07:00

env.sh

build: avoid unbounded parallel builds (#12319)

2025-09-18 14:57:01 -07:00

install.sh

fix: own lib/ollama directory

2025-03-03 13:01:18 -08:00

push_docker.sh

change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347)

2024-03-26 13:04:17 -07:00

tag_latest.sh

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

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