pin nightly to 2.5.0.dev20240709+cu121 (#505)

* pin nightly to 2.5.0.dev20240711+cu121

* push

* Update regression_test.yml

* Update regression_test.yml

Author: msaroufim

.github/workflows/regression_test.yml

@@ -33,7 +33,7 @@ jobs:
             gpu-arch-version: "12.1"
           - name: CUDA Nightly
             runs-on: linux.g5.12xlarge.nvidia.gpu
-            torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cu121'
+            torch-spec: '--pre torch==2.5.0.dev20240709+cu121 --index-url https://download.pytorch.org/whl/nightly/cu121'
             gpu-arch-type: "cuda"
             gpu-arch-version: "12.1"
           - name: CPU 2.2.2
@@ -48,7 +48,7 @@ jobs:
             gpu-arch-version: ""
           - name: CPU Nightly
             runs-on: linux.4xlarge
-            torch-spec: '--pre torch --index-url https://download.pytorch.org/whl/nightly/cpu'
+            torch-spec: '--pre torch==2.5.0.dev20240709+cpu --index-url https://download.pytorch.org/whl/nightly/cpu'
             gpu-arch-type: "cpu"
             gpu-arch-version: ""
 

test/dtypes/test_uint4.py

@@ -4,19 +4,14 @@
     PerChannelSymmetricWeightUInt4Tensor,
 )
 import unittest
-from unittest import TestCase, main
 from torch.ao.quantization.quantize_pt2e import prepare_pt2e, convert_pt2e
 from torch.ao.quantization.quantizer import QuantizationSpec, Quantizer
 
 from torch._export import capture_pre_autograd_graph
-from torch._export import dynamic_dim
 from torch.testing._internal.common_quantization import (
     NodeSpec as ns,
     QuantizationTestCase,
 )
-from torchao.quantization.utils import (
-    compute_error,
-)
 from torchao.quantization.quant_api import (
     _replace_with_custom_fn_if_matches_filter,
 )
@@ -30,7 +25,6 @@
     QuantizationAnnotation,
 )
 import copy
-from packaging import version
 
 
 def _apply_weight_only_uint4_quant(model):
@@ -229,4 +223,4 @@ def forward(self, x):
         )
 
 if __name__ == "__main__":
-    main()
+    unittest.main()