llama-stack-mirror/llama_stack/templates/nvidia
Sébastien Han 98db4a226f
chore(refact)!: simplify config management
We are dropping configuration via CLI flag almost entirely. If any
server configuration has to be tweak it must be done through the server
section in the run.yaml.

This is unfortunately a breaking change for whover was using:

* `--tls-*`
* `--disable_ipv6`

`--port` stays around and get a special treatment since we believe, it's
common for user dev to change port for quick experimentations.

Signed-off-by: Sébastien Han <seb@redhat.com>
2025-05-07 16:39:04 +02:00
..
__init__.py add nvidia distribution (#565) 2025-01-15 14:04:43 -08:00
build.yaml feat: Add NVIDIA NeMo datastore (#1852) 2025-04-28 09:41:59 -07:00
doc_template.md feat: Update NVIDIA to GA docs; remove notebook reference until ready (#1999) 2025-04-18 19:13:18 -04:00
nvidia.py feat: Add NVIDIA NeMo datastore (#1852) 2025-04-28 09:41:59 -07:00
run-with-safety.yaml chore(refact)!: simplify config management 2025-05-07 16:39:04 +02:00
run.yaml chore(refact)!: simplify config management 2025-05-07 16:39:04 +02:00