Merge branch 'kylesayrs/revert-kv-cache-tests' into kylesayrs/quantization-mixin

Author: kylesayrs

.github/workflows/test-check-transformers.yaml

@@ -95,3 +95,7 @@ jobs:
         if: (success() || failure()) && steps.install.outcome == 'success'
         run: |
           pytest -v tests/llmcompressor/transformers/obcq
+      - name: Running KV Cache Tests
+        if: (success() || failure()) && steps.install.outcome == 'success'
+        run: |
+          pytest -v tests/llmcompressor/transformers/kv_cache -k "not test_kv_cache_gptq_model_state_dict_attr"

tests/llmcompressor/transformers/kv_cache/test_kv_cache.py

@@ -222,7 +222,6 @@ def test_kv_cache_gptq_model_state_dict_attr(kv_cache_fixture, tmp_path):
                     dynamic: {dynamic}
                     symmetric: {symmetric}
             GPTQModifier:
-                sequential_update: false
                 ignore: ["lm_head"]
                 config_groups:
                     group_0: