riteshghorse commented on code in PR #29223:
URL: https://github.com/apache/beam/pull/29223#discussion_r1378840628
##########
sdks/python/apache_beam/ml/inference/huggingface_inference.py:
##########
@@ -638,8 +640,30 @@ def __init__(
if max_batch_size is not None:
self._batching_kwargs['max_batch_size'] = max_batch_size
self._large_model = large_model
+
+ # Check if the device is specified twice. If true then the device parameter
+ # of model handler is overridden.
+ self._deduplicate_device_value(device)
_validate_constructor_args_hf_pipeline(self._task, self._model)
+ def _deduplicate_device_value(self, device: str):
+ if 'device' not in self._load_pipeline_args:
+ if device == 'CPU':
+ self._load_pipeline_args['device'] = 'cpu'
+ else:
+ if is_gpu_available_torch():
+ self._load_pipeline_args['device'] = 'cuda:1'
+ else:
+ _LOGGER.warning(
+ "HuggingFaceModelHandler specified a 'GPU' device, "
+ "but GPUs are not available. Switching to CPU.")
+ self._load_pipeline_args['device'] = 'cpu'
+ else:
+ if device:
Review Comment:
Oops I missed changing that to None while I did other changes keeping that
in mind :p.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
