[core] Support custom ascendc kernels in vllm-ascend (#233)

This PR add custom ascendc kernel rotary_embedding support in
vllm-ascend, related CMakeLists and setuptools is also added in this PR.

Related: https://github.com/vllm-project/vllm-ascend/issues/156

---------

Signed-off-by: ganyi <pleaplusone.gy@gmail.com>

csrc/utils.h

@@ -0,0 +1,43 @@
+#pragma once
+
+#include "kernels/types.h"
+#include <c10/core/ScalarType.h>
+#include <Python.h>
+
+#define _CONCAT(A, B) A##B
+#define CONCAT(A, B) _CONCAT(A, B)
+
+#define _STRINGIFY(A) #A
+#define STRINGIFY(A) _STRINGIFY(A)
+
+// A version of the TORCH_LIBRARY macro that expands the NAME, i.e. so NAME
+// could be a macro instead of a literal token.
+#define TORCH_LIBRARY_EXPAND(NAME, MODULE) TORCH_LIBRARY(NAME, MODULE)
+
+// A version of the TORCH_LIBRARY_IMPL macro that expands the NAME, i.e. so NAME
+// could be a macro instead of a literal token.
+#define TORCH_LIBRARY_IMPL_EXPAND(NAME, DEVICE, MODULE) \
+  TORCH_LIBRARY_IMPL(NAME, DEVICE, MODULE)
+
+// REGISTER_EXTENSION allows the shared library to be loaded and initialized
+// via python's import statement.
+#define REGISTER_EXTENSION(NAME)                                               \
+  PyMODINIT_FUNC CONCAT(PyInit_, NAME)() {                                     \
+    static struct PyModuleDef module = {PyModuleDef_HEAD_INIT,                 \
+                                        STRINGIFY(NAME), nullptr, 0, nullptr}; \
+    return PyModule_Create(&module);                                           \
+  }
+
+
+namespace vllm_ascend {
+AscendType get_dtype_from_torch(at::ScalarType scalarType)
+{
+    if (scalarType == at::ScalarType::Float) {
+        return AscendType::FP32;
+    } else if (scalarType == at::ScalarType::BFloat16) {
+        return AscendType::BF16;
+    } else {
+        return AscendType::FP16;
+    }
+}
+} // namespace vllm_ascend