mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-29 03:14:19 +00:00
This simplifies the passing of config attributes when constructing the Ollama inference adapter so that we just pass the config in instead of every attribute on the config as a separate parameter. Signed-off-by: Ben Browning <bbrownin@redhat.com> |
||
---|---|---|
.. | ||
agents | ||
datasetio | ||
eval | ||
inference | ||
post_training | ||
safety | ||
tool_runtime | ||
vector_io | ||
__init__.py |