mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-08 21:04:39 +00:00
feat: add refresh_models support to inference adapters (default: false) (#3719)
# What does this PR do? inference adapters can now configure `refresh_models: bool` to control periodic model listing from their providers BREAKING CHANGE: together inference adapter default changed. previously always refreshed, now follows config. addresses "models: refresh" on #3517 ## Test Plan ci w/ new tests
This commit is contained in:
parent
8b9af03a1b
commit
e892a3f7f4
31 changed files with 33 additions and 67 deletions
|
@ -41,9 +41,6 @@ class DatabricksInferenceAdapter(OpenAIMixin):
|
|||
).serving_endpoints.list() # TODO: this is not async
|
||||
]
|
||||
|
||||
async def should_refresh_models(self) -> bool:
|
||||
return False
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue