Move qualcomm.passes to qualcomm._passes (#5920)

Summary:
Changing qualcomm.passes to qualcomm._passes to indicate that these passes are not covered under the API stability guarantee.

Pull Request resolved: #5920

Reviewed By: helunwencser

Differential Revision: D63926845

fbshipit-source-id: f1e3187f3012f83b388d9635ca5a244fa36950d6
(cherry picked from commit 866b40c)

Author: tarun292

backends/qualcomm/README.md

@@ -46,7 +46,7 @@ backends/qualcomm
 |   └── python # Python interface for using QNN libraries.
 ├── builders # Codes for lowering each operators (AoT Part).
 ├── partition # QNN Partitioner (AoT Part).
-├── passes # Various passes helping lower models to QNN backend (AoT Part).
+├── _passes # Various private passes helping lower models to QNN backend (AoT Part).
 ├── python # Places to put pybind artifacts for accessing QNN APIs, structures, etc (AoT Part).
 ├── quantizer # QNN Quantizer
 ├── runtime # Here is QNN runtime responsbile for compiling a model on x64.

backends/qualcomm/_passes/TARGETS

@@ -0,0 +1,18 @@
+load("@fbsource//xplat/executorch/build:runtime_wrapper.bzl", "runtime")
+
+oncall("executorch")
+
+runtime.python_library(
+    name = "passes",
+    srcs = glob([
+        "*.py",
+    ]),
+    visibility = [
+        "@EXECUTORCH_CLIENTS",
+    ],
+    deps = [
+        "//executorch/backends/transforms:addmm_mm_to_linear",
+        "//executorch/exir/backend:backend_details",
+        "//executorch/exir/backend:compile_spec_schema",
+    ],
+)