Bump iree to 20231130.724

To solve the batchnorm2d issue nod-ai#110
Xfail llama_test becasue missing ops from torch to linalg

Author: AmosLewis

requirements.txt

@@ -7,5 +7,5 @@
 -r pytorch-cpu-requirements.txt
 -r torchvision-requirements.txt
 
-iree-compiler==20231121.715
-iree-runtime==20231121.715
+iree-compiler==20231130.724
+iree-runtime==20231130.724

tests/dynamo/llama_test.py

@@ -12,6 +12,7 @@
 
 import math
 import unittest
+import pytest
 from dataclasses import dataclass
 from typing import Any, Optional, Tuple
 
@@ -314,6 +315,7 @@ def main():
     opt(example_tokens, start_pos)
 
 
+@pytest.mark.xfail(reason="https://github.com/nod-ai/SHARK-Turbine/issues/221")
 class ModelTests(unittest.TestCase):
     def testLLama(self):
         main()

tests/importers/onnx_importer/import_smoke_test.py

@@ -40,16 +40,6 @@
     "node_test_ai_onnx_ml_label_encoder_string_int_no_default_model",
     "node_test_ai_onnx_ml_label_encoder_tensor_mapping_model",
     "node_test_ai_onnx_ml_label_encoder_tensor_value_only_mapping_model",
-    "node_test_bitshift_left_uint16_model",
-    "node_test_bitshift_left_uint32_model",
-    "node_test_bitshift_left_uint64_model",
-    "node_test_bitshift_right_uint16_model",
-    "node_test_bitshift_right_uint32_model",
-    "node_test_bitshift_right_uint64_model",
-    "node_test_bitwise_and_ui64_bcast_3v1d_model",
-    "node_test_bitwise_not_3d_model",
-    "node_test_bitwise_or_ui64_bcast_3v1d_model",
-    "node_test_bitwise_xor_ui64_bcast_3v1d_model",
     "node_test_cast_FLOAT16_to_FLOAT8E4M3FNUZ_model",
     "node_test_cast_FLOAT16_to_FLOAT8E4M3FN_model",
     "node_test_cast_FLOAT16_to_FLOAT8E5M2FNUZ_model",
@@ -166,15 +156,6 @@
     "node_test_lstm_defaults_model",
     "node_test_lstm_with_initial_bias_model",
     "node_test_lstm_with_peepholes_model",
-    "node_test_max_uint16_model",
-    "node_test_max_uint32_model",
-    "node_test_max_uint64_model",
-    "node_test_min_uint16_model",
-    "node_test_min_uint32_model",
-    "node_test_min_uint64_model",
-    "node_test_mod_uint16_model",
-    "node_test_mod_uint32_model",
-    "node_test_mod_uint64_model",
     "node_test_optional_get_element_optional_sequence_model",
     "node_test_optional_get_element_optional_tensor_model",
     "node_test_optional_get_element_sequence_model",
@@ -183,8 +164,6 @@
     "node_test_optional_has_element_empty_optional_input_model",
     "node_test_optional_has_element_optional_input_model",
     "node_test_optional_has_element_tensor_input_model",
-    "node_test_pow_types_float32_uint32_model",
-    "node_test_pow_types_float32_uint64_model",
     "node_test_quantizelinear_e4m3fn_model",
     "node_test_quantizelinear_e5m2_model",
     "node_test_range_float_type_positive_delta_expanded_model",