phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 02:49:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: separate build and run provider types

Browse source 
in #2637, I combined the run and build config provider types to both use `Provider`

since this includes a provider_id, a user must now specify this when writing a build yaml. This is not very clear because all a user should care about upon build is the code to be installed (the module and the provider_type)

introduce `BuildProvider` and fixup the parts of the code impacted by this

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-07-25 14:34:06 -04:00
parent 025163d8e6
commit 236a670fc1
19 changed files with 401 additions and 754 deletions
Download patch file Download diff file Expand all files Collapse all files

70
llama_stack/templates/nvidia/nvidia.py
View file

@ -6,7 +6,7 @@
from pathlib import Path
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
from llama_stack.distribution.datatypes import BuildProvider, ModelInput, Provider, ShieldInput, ToolGroupInput
from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig
from llama_stack.providers.remote.eval.nvidia import NVIDIAEvalConfig
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
@ -17,65 +17,19 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
def get_distribution_template() -> DistributionTemplate:
providers = {
"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={})],
"inference": [BuildProvider(provider_type="remote::nvidia")],
"vector_io": [BuildProvider(provider_type="inline::faiss")],
"safety": [BuildProvider(provider_type="remote::nvidia")],
"agents": [BuildProvider(provider_type="inline::meta-reference")],
"telemetry": [BuildProvider(provider_type="inline::meta-reference")],
"eval": [BuildProvider(provider_type="remote::nvidia")],
"post_training": [BuildProvider(provider_type="remote::nvidia")],
"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",
)
BuildProvider(provider_type="inline::localfs"),
BuildProvider(provider_type="remote::nvidia"),
],
"scoring": [BuildProvider(provider_type="inline::basic")],
"tool_runtime": [BuildProvider(provider_type="inline::rag-runtime")],
}
inference_provider = Provider(