update

Author: DN6

.github/workflows/nightly_tests.yml

@@ -356,6 +356,8 @@ jobs:
         config:
           - backend: "bitsandbytes"
             test_location: "bnb"
+          - backend: "gguf"
+            test_location: "gguf"
     runs-on:
       group: aws-g6e-xlarge-plus
     container:
@@ -519,4 +521,4 @@ jobs:
 #        if: always()
 #        run: |
 #          pip install slack_sdk tabulate
-#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY

tests/quantization/gguf/test_gguf.py

@@ -75,7 +75,7 @@ def test_gguf_linear_layers(self):
             if isinstance(module, torch.nn.Linear) and hasattr(module.weight, "quant_type"):
                 assert module.weight.dtype == torch.uint8
 
-    def test_gguf_memory(self):
+    def test_gguf_memory_usage(self):
         quantization_config = GGUFQuantizationConfig(compute_dtype=self.torch_dtype)
 
         model = FluxTransformer2DModel.from_single_file(