Re-enable test_8da4w_quantizer on 2.3 (pytorch#107)

* Re-enable test_8da4w_quantizer on 2.3

* Update test_quant_api.py

* Update test_quant_api.py

Author: cpuhrsch

test/quantization/test_quant_api.py

@@ -159,7 +159,7 @@ def test_int8_wo_quant_save_load(self):
 
         torch.testing.assert_close(ref, res.cpu())
 
-    @unittest.skipIf(not TORCH_VERSION_AFTER_2_4, "skipping when torch verion is 2.4 or lower")
+    @unittest.skipIf(not TORCH_VERSION_AFTER_2_3, "skipping when torch verion is 2.3 or lower")
     def test_8da4w_quantizer(self):
         from torchao.quantization.quant_api import Int8DynActInt4WeightQuantizer
         from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear