Anuraag (Rag) Agrawal e28f2d4900 openai: return usage as final chunk for streams (#6784)		il y a 4 mois
..
images	1713eddcd0 Fix import image width (#6528)	il y a 8 mois
README.md	8cc0ee2efe Doc container usage and workaround for nvidia errors	il y a 11 mois
api.md	527cc97899 llama: update vendored code to commit 40c6d79f (#7875)	il y a 4 mois
development.md	82a02e18d9 build: fix typo in override variable (#8031)	il y a 4 mois
docker.md	a0ea067b63 build: fix arm container image (#7674)	il y a 5 mois
faq.md	1bdab9fdb1 llm: introduce k/v context quantization (vRAM improvements) (#6279)	il y a 4 mois
gpu.md	4879a234c4 build: Make target improvements (#7499)	il y a 4 mois
import.md	2f0a8c8778 docs: fix minor typo in import.md (#7764)	il y a 5 mois
linux.md	4879a234c4 build: Make target improvements (#7499)	il y a 4 mois
modelfile.md	2b82c5a8a1 docs: correct default num_predict value in modelfile.md (#7693)	il y a 4 mois
openai.md	e28f2d4900 openai: return usage as final chunk for streams (#6784)	il y a 4 mois
template.md	55ea963c9e update default model to llama3.2 (#6959)	il y a 7 mois
troubleshooting.md	abfdc4710f all: fix typos in documentation, code, and comments (#7021)	il y a 4 mois
tutorials.md	85951d25ef Created tutorial for running Ollama on NVIDIA Jetson devices (#1098)	il y a 1 an
windows.md	4879a234c4 build: Make target improvements (#7499)	il y a 4 mois

Documentation