Tree: e2c3f6b3e2

History

Daniel Hiltgen 283948c83b Adjust windows ROCm discovery The v5 hip library returns unsupported GPUs which wont enumerate at inference time in the runner so this makes sure we align discovery. The gfx906 cards are no longer supported so we shouldn't compile with that GPU type as it wont enumerate at runtime.		2 years ago
..
tutorials	add embed model command and fix question invoke (#4766)	2 years ago
README.md	Doc container usage and workaround for nvidia errors	2 years ago
api.md	Update api.md	2 years ago
development.md	update llama.cpp submodule to `d7fd29f` (#5475)	2 years ago
docker.md	Doc container usage and workaround for nvidia errors	2 years ago
faq.md	Bump ROCm on windows to 6.1.2	2 years ago
gpu.md	Adjust windows ROCm discovery	2 years ago
import.md	Update import.md	2 years ago
linux.md	Add instructions to easily install specific versions on faq.md (#4084)	2 years ago
modelfile.md	Update 'llama2' -> 'llama3' in most places (#4116)	2 years ago
openai.md	OpenAI: Add Suffix to `v1/completions` (#5611)	2 years ago
troubleshooting.md	Document older win10 terminal problems	2 years ago
tutorials.md	Created tutorial for running Ollama on NVIDIA Jetson devices (#1098)	2 years ago
windows.md	Document older win10 terminal problems	2 years ago

Documentation