phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 14:38:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: separate build and run provider types (#2917)
Some checks failed
Coverage Badge / unit-tests (push) Failing after 1s
Details
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Details
Integration Tests / discover-tests (push) Successful in 3s
Details
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 4s
Details
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 4s
Details
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 5s
Details
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 5s
Details
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 4s
Details
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 5s
Details
Test Llama Stack Build / generate-matrix (push) Successful in 4s
Details
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 5s
Details
Python Package Build Test / build (3.13) (push) Failing after 2s
Details
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Details
Python Package Build Test / build (3.12) (push) Failing after 2s
Details
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 5s
Details
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 6s
Details
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
Details
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 5s
Details
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Details
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 5s
Details
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 9s
Details
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Failing after 6s
Details
Test External API and Providers / test-external (venv) (push) Failing after 5s
Details
Update ReadTheDocs / update-readthedocs (push) Failing after 4s
Details
Unit Tests / unit-tests (3.13) (push) Failing after 5s
Details
Test Llama Stack Build / build (push) Failing after 3s
Details
Unit Tests / unit-tests (3.12) (push) Failing after 5s
Details
Integration Tests / test-matrix (push) Failing after 7s
Details
Pre-commit / pre-commit (push) Successful in 1m13s
Details

Browse source 
# What does this PR do?

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 15:39:26 -04:00 • committed by GitHub
parent 025163d8e6
commit 3344d8a9e5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 401 additions and 754 deletions
Download patch file Download diff file Expand all files Collapse all files

51
llama_stack/templates/meta-reference-gpu/build.yaml
View file

@ -3,48 +3,31 @@ distribution_spec:
description: Use Meta Reference for running LLM inference
providers:
inference:
- provider_id: meta-reference
provider_type: inline::meta-reference
- provider_type: inline::meta-reference
vector_io:
- provider_id: faiss
provider_type: inline::faiss
- provider_id: chromadb
provider_type: remote::chromadb
- provider_id: pgvector
provider_type: remote::pgvector
- provider_type: inline::faiss
- provider_type: remote::chromadb
- provider_type: remote::pgvector
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
- provider_type: inline::llama-guard
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
- provider_type: inline::meta-reference
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
- provider_type: inline::meta-reference
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
- provider_type: inline::meta-reference
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
- provider_id: localfs
provider_type: inline::localfs
- provider_type: remote::huggingface
- provider_type: inline::localfs
scoring:
- provider_id: basic
provider_type: inline::basic
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
- provider_id: braintrust
provider_type: inline::braintrust
- provider_type: inline::basic
- provider_type: inline::llm-as-judge
- provider_type: inline::braintrust
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
- provider_id: tavily-search
provider_type: remote::tavily-search
- provider_id: rag-runtime
provider_type: inline::rag-runtime
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
- provider_type: remote::brave-search
- provider_type: remote::tavily-search
- provider_type: inline::rag-runtime
- provider_type: remote::model-context-protocol
image_type: conda
image_name: meta-reference-gpu
additional_pip_packages:

96
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -8,6 +8,7 @@ from pathlib import Path
from llama_stack.apis.models import ModelType
from llama_stack.distribution.datatypes import (
BuildProvider,
ModelInput,
Provider,
ShieldInput,
@ -25,91 +26,30 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": [
Provider(
provider_id="meta-reference",
provider_type="inline::meta-reference",
)
],
"inference": [BuildProvider(provider_type="inline::meta-reference")],
"vector_io": [
Provider(
provider_id="faiss",
provider_type="inline::faiss",
),
Provider(
provider_id="chromadb",
provider_type="remote::chromadb",
),
Provider(
provider_id="pgvector",
provider_type="remote::pgvector",
),
],
"safety": [
Provider(
provider_id="llama-guard",
provider_type="inline::llama-guard",
)
],
"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="meta-reference",
provider_type="inline::meta-reference",
)
BuildProvider(provider_type="inline::faiss"),
BuildProvider(provider_type="remote::chromadb"),
BuildProvider(provider_type="remote::pgvector"),
],
"safety": [BuildProvider(provider_type="inline::llama-guard")],
"agents": [BuildProvider(provider_type="inline::meta-reference")],
"telemetry": [BuildProvider(provider_type="inline::meta-reference")],
"eval": [BuildProvider(provider_type="inline::meta-reference")],
"datasetio": [
Provider(
provider_id="huggingface",
provider_type="remote::huggingface",
),
Provider(
provider_id="localfs",
provider_type="inline::localfs",
),
BuildProvider(provider_type="remote::huggingface"),
BuildProvider(provider_type="inline::localfs"),
],
"scoring": [
Provider(
provider_id="basic",
provider_type="inline::basic",
),
Provider(
provider_id="llm-as-judge",
provider_type="inline::llm-as-judge",
),
Provider(
provider_id="braintrust",
provider_type="inline::braintrust",
),
BuildProvider(provider_type="inline::basic"),
BuildProvider(provider_type="inline::llm-as-judge"),
BuildProvider(provider_type="inline::braintrust"),
],
"tool_runtime": [
Provider(
provider_id="brave-search",
provider_type="remote::brave-search",
),
Provider(
provider_id="tavily-search",
provider_type="remote::tavily-search",
),
Provider(
provider_id="rag-runtime",
provider_type="inline::rag-runtime",
),
Provider(
provider_id="model-context-protocol",
provider_type="remote::model-context-protocol",
),
BuildProvider(provider_type="remote::brave-search"),
BuildProvider(provider_type="remote::tavily-search"),
BuildProvider(provider_type="inline::rag-runtime"),
BuildProvider(provider_type="remote::model-context-protocol"),
],
}
name = "meta-reference-gpu"