fix call

Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>

Author: kylesayrs

tests/llmcompressor/transformers/tracing/test_models.py

@@ -136,7 +136,6 @@ def test_model_trace(model_id, model_class, targets, modality, backends):
         modality=modality,
         trust_remote_code=True,
         skip_weights=True,
-        device_map="cpu",
     )
 
     target_modules = get_target_modules(model, targets)

tests/lmeval/test_lmeval.py

@@ -90,7 +90,6 @@ def set_up(self, test_data_file: str):
         logger.info("========== RUNNING ==============")
         logger.info(self.scheme)
 
-        self.device = "cuda:0"
         self.num_calibration_samples = 512
         self.max_seq_length = 2048
 
@@ -103,7 +102,6 @@ def test_lm_eval(self, test_data_file: str):
         oneshot_model, processor = run_oneshot_for_e2e_testing(
             model=self.model,
             model_class=self.model_class,
-            device=self.device,
             num_calibration_samples=self.num_calibration_samples,
             max_seq_length=self.max_seq_length,
             scheme=self.scheme,