phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 21:34:36 +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

82
llama_stack/distributions/nvidia/run.yaml
View file

@ -85,88 +85,88 @@ inference_store:
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
models:
- metadata: {}
model_id: meta/llama3-8b-instruct
provider_id: nvidia
provider_model_id: meta/llama3-8b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama3-70b-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama3-70b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.1-8b-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.1-8b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.1-70b-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.1-70b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.1-405b-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.1-405b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-1b-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-3b-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.2-3b-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-11b-vision-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.2-11b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.2-90b-vision-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.3-70b-instruct
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: meta/llama-3.3-70b-instruct
model_type: llm
- metadata: {}
model_id: nvidia/vila
provider_id: nvidia
provider_model_id: nvidia/vila
model_type: llm
use_provider_model_id_as_id: false
- metadata: {}
provider_model_id: nvidia/vila
provider_id: nvidia
model_type: llm
use_provider_model_id_as_id: false
- metadata:
embedding_dimension: 2048
context_length: 8192
model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
provider_id: nvidia
provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
provider_id: nvidia
model_type: embedding
use_provider_model_id_as_id: false
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: nvidia/nv-embedqa-e5-v5
provider_id: nvidia
provider_model_id: nvidia/nv-embedqa-e5-v5
provider_id: nvidia
model_type: embedding
use_provider_model_id_as_id: false
- metadata:
embedding_dimension: 4096
context_length: 512
model_id: nvidia/nv-embedqa-mistral-7b-v2
provider_id: nvidia
provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
provider_id: nvidia
model_type: embedding
use_provider_model_id_as_id: false
- metadata:
embedding_dimension: 1024
context_length: 512
model_id: snowflake/arctic-embed-l
provider_id: nvidia
provider_model_id: snowflake/arctic-embed-l
provider_id: nvidia
model_type: embedding
use_provider_model_id_as_id: false
shields: []
vector_dbs: []
datasets: []