Add exception free quantized kernels (pytorch#14962)

Summary:

Explicitly declaring generated libs with exception code off for quantized kernels as executorch does not use exceptions in general, and it can cause downstream errors. Detailed error is P1986979595 but the relevant part is:
```
buck-out/ABC/gen/fbsource/6e53edb0a9a0d828/xplat/executorch/kernels/quantized/__generated_lib_combined__/out/RegisterCodegenUnboxedKernelsEverything.cpp:77:44: error: exception handling disabled, use '-fexceptions' to enable
   77 |             } catch (const std::exception& ex) {
      |
```
This means the existing generated code uses exceptions in its code, so when we use these kernels with -fno-exceptions downstream, the build fails.

After this diff, we can use the exception free kernels with 'no_exceptions' suffix -- 
`//xplat/executorch/kernels/quantized:generated_lib_no_exceptions` or 
`//xplat/executorch/kernels/quantized:generated_lib_aten_no_exceptions` as appropriate. 

We still have `//xplat/executorch/kernels/quantized:generated_lib` and `//xplat/executorch/kernels/quantized:generated_lib_aten` available, same as before, so no downstream side effects are expected.

Reviewed By: swolchok

Differential Revision: D84284541

Author: Daksh-Shami

kernels/quantized/targets.bzl

@@ -96,41 +96,46 @@ def define_common_targets():
             ],
         )
 
-        executorch_generated_lib(
-            name = "generated_lib" + aten_suffix,
-            deps = [
-                ":quantized_operators" + aten_suffix,
-                ":all_quantized_ops",
-            ],
-            custom_ops_yaml_target = ":quantized.yaml",
-            custom_ops_aten_kernel_deps = [":quantized_operators_aten"] if aten_mode else [],
-            custom_ops_requires_aot_registration = False,
-            aten_mode = aten_mode,
-            visibility = [
-                "//executorch/...",
-                "@EXECUTORCH_CLIENTS",
-            ],
-            define_static_targets = True,
-        )
+        for support_exceptions in [True, False]:
+            exception_suffix = "_no_exceptions" if not support_exceptions else ""
 
-        # On Windows we can only compile these two ops currently, so adding a
-        # separate target for this.
-        executorch_generated_lib(
-            name = "q_dq_ops_generated_lib" + aten_suffix,
-            custom_ops_yaml_target = ":quantized.yaml",
-            kernel_deps = [
-                "//executorch/kernels/quantized/cpu:op_quantize" + aten_suffix,
-                "//executorch/kernels/quantized/cpu:op_dequantize" + aten_suffix,
-            ],
-            aten_mode = aten_mode,
-            deps = [
-                ":q_dq_ops",
-            ],
-            visibility = [
-                "//executorch/...",
-                "@EXECUTORCH_CLIENTS",
-            ],
-        )
+            executorch_generated_lib(
+                name = "generated_lib" + aten_suffix + exception_suffix,
+                deps = [
+                    ":quantized_operators" + aten_suffix,
+                    ":all_quantized_ops",
+                ],
+                custom_ops_yaml_target = ":quantized.yaml",
+                custom_ops_aten_kernel_deps = [":quantized_operators_aten"] if aten_mode else [],
+                custom_ops_requires_aot_registration = False,
+                aten_mode = aten_mode,
+                support_exceptions = support_exceptions,
+                visibility = [
+                    "//executorch/...",
+                    "@EXECUTORCH_CLIENTS",
+                ],
+                define_static_targets = True,
+            )
+
+            # On Windows we can only compile these two ops currently, so adding a
+            # separate target for this.
+            executorch_generated_lib(
+                name = "q_dq_ops_generated_lib" + aten_suffix + exception_suffix,
+                custom_ops_yaml_target = ":quantized.yaml",
+                kernel_deps = [
+                    "//executorch/kernels/quantized/cpu:op_quantize" + aten_suffix,
+                    "//executorch/kernels/quantized/cpu:op_dequantize" + aten_suffix,
+                ],
+                aten_mode = aten_mode,
+                deps = [
+                    ":q_dq_ops",
+                ],
+                support_exceptions = support_exceptions,
+                visibility = [
+                    "//executorch/...",
+                    "@EXECUTORCH_CLIENTS",
+                ],
+            )
 
     runtime.python_library(
         name = "quantized_ops_lib",