phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 20:12:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

clarifying register model

Browse source
This commit is contained in:
Justin 2025-10-06 15:09:38 -04:00
parent 0ba4cd460f
commit b519434c88
1 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/remote/inference/runpod/runpod.py
View file

@ -93,10 +93,13 @@ class RunpodInferenceAdapter(OpenAIMixin):
async def register_model(self, model: Model) -> Model: async def register_model(self, model: Model) -> Model:
""" """
Register a model and verify it's available on the RunPod endpoint. Register a model and verify it's available on the RunPod endpoint.
In the .yaml file the model: can be defined as example This is mainly if you want to register a model with a custom identifier.
This will ping the endpoint and make sure the model is avaliable via the /v1/models.
In the .yaml file the model: can be defined as example.
models: models:
- metadata: {} - metadata: {}
model_id: qwen3-32b-awq model_id: custom_model_id
model_type: llm model_type: llm
provider_id: runpod provider_id: runpod
provider_model_id: Qwen/Qwen3-32B-AWQ provider_model_id: Qwen/Qwen3-32B-AWQ