phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 04:40:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'meta-llama:main' into feat/litellm_sambanova_usage

Browse source
This commit is contained in:
Jorge Piedrahita Ortiz 2025-04-10 11:01:51 -05:00 • committed by GitHub
commit 13c660f5a5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
57 changed files with 10986 additions and 93 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -307,9 +307,10 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
if model.model_type == ModelType.embedding:
logger.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
await self.client.pull(model.provider_resource_id)
response = await self.client.list()
else:
response = await self.client.ps()
# we use list() here instead of ps() -
# - ps() only lists running models, not available models
# - models not currently running are run by the ollama server as needed
response = await self.client.list()
available_models = [m["model"] for m in response["models"]]
if model.provider_resource_id not in available_models:
raise ValueError(