Add handle cache for AMD platform (#698)

Introduce handle cache for AMD platform.
Avoid reaching handle limitation if we open too much IPC handles

For nvidia, we don't need this feature since nvidia will count the
handle reference internally and reuse the same handle if already be
opened

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Binyang2014 <9415966+Binyang2014@users.noreply.github.com>
Co-authored-by: Changho Hwang <changhohwang@microsoft.com>

python/mscclpp/utils.py

@@ -123,7 +123,7 @@ class KernelBuilder:
         if self.macros:
             command += self.macros
         try:
-            subprocess.run(command, capture_output=True, text=True, check=True, bufsize=1)
+            subprocess.run(command, capture_output=True, text=True, check=True, bufsize=1, stdin=subprocess.DEVNULL)
             with open(f"{self._tempdir.name}/{output_file}", "rb") as f:
                 return f.read()
         except subprocess.CalledProcessError as e: