phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 06:28:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: re-work distro-codegen

Browse source 
each *.py file in the various templates now has to use `Provider`s rather than the stringified provider_types in the DistributionTemplate. Adjust that, regenerate all templates, docs, etc.

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-07-06 20:06:27 -04:00
parent dcc6b1eee9
commit 776fabed9e
28 changed files with 809 additions and 328 deletions
Download patch file Download diff file Expand all files Collapse all files

69
llama_stack/templates/nvidia/nvidia.py
View file

@ -17,16 +17,65 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["remote::nvidia"],
"vector_io": ["inline::faiss"],
"safety": ["remote::nvidia"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
"eval": ["remote::nvidia"],
"post_training": ["remote::nvidia"],
"datasetio": ["inline::localfs", "remote::nvidia"],
"scoring": ["inline::basic"],
"tool_runtime": ["inline::rag-runtime"],
"inference": [
Provider(
provider_id="nvidia",
provider_type="remote::nvidia",
)
],
"vector_io": [
Provider(
provider_id="faiss",
provider_type="inline::faiss",
)
],
"safety": [
Provider(
provider_id="nvidia",
provider_type="remote::nvidia",
)
],
"agents": [
Provider(
provider_id="meta-reference",
provider_type="inline::meta-reference",
)
],
"telemetry": [
Provider(
provider_id="meta-reference",
provider_type="inline::meta-reference",
)
],
"eval": [
Provider(
provider_id="nvidia",
provider_type="remote::nvidia",
)
],
"post_training": [Provider(provider_id="nvidia", provider_type="remote::nvidia", config={})],
"datasetio": [
Provider(
provider_id="localfs",
provider_type="inline::localfs",
),
Provider(
provider_id="nvidia",
provider_type="remote::nvidia",
),
],
"scoring": [
Provider(
provider_id="basic",
provider_type="inline::basic",
)
],
"tool_runtime": [
Provider(
provider_id="rag-runtime",
provider_type="inline::rag-runtime",
)
],
}
inference_provider = Provider(