Skip to content
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions inference/core/interfaces/http/http_api.py
Original file line number Diff line number Diff line change
Expand Up @@ -1625,7 +1625,6 @@ async def consume(
# Enable preloading models at startup
if (
(PRELOAD_MODELS or DEDICATED_DEPLOYMENT_WORKSPACE_URL)
and API_KEY
and not (LAMBDA or GCP_SERVERLESS)
):

Expand Down Expand Up @@ -1662,7 +1661,7 @@ def load_model(model_id):
state.initialization_errors.append((model_id, str(e)))
logger.debug(f"load_model({model_id}) - finished")

if PRELOAD_MODELS:
if PRELOAD_MODELS and API_KEY:
# Create tasks for each model to be loaded
model_loading_executor = ThreadPoolExecutor(max_workers=2)
loaded_futures: List[Tuple[str, Future]] = []
Expand Down