phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 21:48:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: allow user to register model alias explicitly, tests

Browse source 
# What does this PR do?

Context: https://github.com/llamastack/llama-stack/discussions/3483

This PR enables the registering `provider_model_id` as the model identifier without breaking backward compatibility.


## Test Plan
todo
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-09-18 15:47:20 -07:00
parent ac1414b571
commit 83a229554b
20 changed files with 236 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/distributions/dell/dell.py
View file

@ -79,15 +79,15 @@ def get_distribution_template() -> DistributionTemplate:
)
inference_model = ModelInput(
model_id="${env.INFERENCE_MODEL}",
provider_model_id="${env.INFERENCE_MODEL}",
provider_id="tgi0",
)
safety_model = ModelInput(
model_id="${env.SAFETY_MODEL}",
provider_model_id="${env.SAFETY_MODEL}",
provider_id="tgi1",
)
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_model_id="all-MiniLM-L6-v2",
provider_id="sentence-transformers",
model_type=ModelType.embedding,
metadata={

9
llama_stack/distributions/dell/run-with-safety.yaml
View file

@ -103,18 +103,21 @@ inference_store:
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_model_id: ${env.INFERENCE_MODEL}
provider_id: tgi0
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
model_id: ${env.SAFETY_MODEL}
provider_model_id: ${env.SAFETY_MODEL}
provider_id: tgi1
model_type: llm
use_provider_model_id_as_id: false
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
use_provider_model_id_as_id: false
shields:
- shield_id: ${env.SAFETY_MODEL}
vector_dbs: []

6
llama_stack/distributions/dell/run.yaml
View file

@ -99,14 +99,16 @@ inference_store:
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_model_id: ${env.INFERENCE_MODEL}
provider_id: tgi0
model_type: llm
use_provider_model_id_as_id: false
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
use_provider_model_id_as_id: false
shields: []
vector_dbs: []
datasets: []