Fix CI/CD failures (#2359)

SUMMARY:

autoround:
- Test was previously using int weights with float activations which
silently fails with torch 2.9 but results in a failure for 2.10
- Fix the args to appropriately use a valid scheme where weights are
also float

quant_reload:
- Remove old unused argument
- Set tie_word_embeddings to false to account for what the test is
targeting - I believe we’re seeing this now from recent
compressed-tensors changes cc @kylesayrs

Author: dsikka

tests/llmcompressor/transformers/autoround/test_autoround_oneshot.py

@@ -56,7 +56,7 @@
     config_groups={
         "group_0": QuantizationScheme(
             targets=["Linear"],
-            weights=QuantizationArgs(num_bits=8, strategy="channel"),
+            weights=QuantizationArgs(num_bits=8, type="float", strategy="channel"),
             input_activations=QuantizationArgs(
                 num_bits=8, type="float", strategy="token", dynamic=True
             ),

tests/llmcompressor/transformers/compression/test_compress_tensor_utils.py

@@ -175,7 +175,7 @@ def test_quant_model_reload(format, dtype, tmp_path):
         concatenate_data=concatenate_data,
         splits=splits,
         precision=dtype,
-        clear_sparse_session=False,
+        tie_word_embeddings=False,
     )
 
     # Fetch the oneshot model