We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 65f4cc3 commit 741d0a6Copy full SHA for 741d0a6
src/sagemaker/serve/builder/model_builder.py
@@ -1293,6 +1293,9 @@ def _model_builder_optimize_wrapper(
1293
max_runtime_in_sec=max_runtime_in_sec,
1294
)
1295
1296
+ if sharding_config:
1297
+ self.pysdk_model._is_sharded_model = True
1298
+
1299
if input_args:
1300
self.sagemaker_session.sagemaker_client.create_optimization_job(**input_args)
1301
job_status = self.sagemaker_session.wait_for_optimization_job(job_name)
@@ -1302,9 +1305,6 @@ def _model_builder_optimize_wrapper(
1302
1305
if not speculative_decoding_config:
1303
1306
self.pysdk_model.remove_tag_with_key(Tag.SPECULATIVE_DRAFT_MODEL_PROVIDER)
1304
1307
- if sharding_config:
- self.pysdk_model._is_sharded_model = True
-
1308
return self.pysdk_model
1309
1310
def _optimize_for_hf(
0 commit comments