ollama/docs
Daniel Hiltgen 4fcc030739
Reduce default parallelism to 1 (#11330)
The current scheduler algorithm of picking the paralellism based on available
VRAM complicates the upcoming dynamic layer memory allocation algorithm.  This
changes the default to 1, with the intent going forward that parallelism is
explicit and will no longer be dynamically determined.  Removal of the dynamic
logic will come in a follow up.
2025-12-29 06:39:41 -06:00
..
images Fix import image width (#6528) 2024-08-27 14:19:47 -07:00
README.md docs: fix path to examples (#8438) 2025-01-15 11:49:12 -08:00
api.md add `tool_name` to api.md (#11326) 2025-12-29 06:39:41 -06:00
development.md docs: fix typo in development.md (#10998) 2025-12-29 06:38:11 -06:00
docker.md docs: improve syntax highlighting in code blocks (#8854) 2025-02-07 09:55:07 -08:00
examples.md examples: remove codified examples (#8267) 2025-01-13 11:26:22 -08:00
faq.md Reduce default parallelism to 1 (#11330) 2025-12-29 06:39:41 -06:00
gpu.md doc: add NVIDIA blackwell to supported list (#11307) 2025-12-29 06:39:40 -06:00
import.md docs: remove unsupported quantizations (#10842) 2025-12-29 06:38:07 -06:00
linux.md docs: update link to AMD drivers in linux.md (#10973) 2025-12-29 06:38:12 -06:00
modelfile.md api: remove unused sampling parameters (#10581) 2025-12-29 06:37:54 -06:00
openai.md docs: improve syntax highlighting in code blocks (#8854) 2025-02-07 09:55:07 -08:00
template.md docs: change more template blocks to have syntax highlighting 2025-12-29 06:37:39 -06:00
troubleshooting.md Re-remove cuda v11 (#10694) 2025-12-29 06:38:18 -06:00
windows.md cleanup: remove OLLAMA_TMPDIR and references to temporary executables (#10182) 2025-04-08 15:01:39 -07:00