Qualcomm AI Engine Direct - Update quant recipe for PyTorch version bump (pytorch#21237)

### Summary
After the PyTorch version bump, the module path changed from
layers.0.attention.wv_conv to
layers.0.attention.forward.__self__.wv_conv Because of this, the
existing regex r"layers\..*\.attention\.wv.*" no longer matches and the
tag is missed. Updating it to r"layers\..*\.attention\..*wv.*" will
cover both formats.

### Test plan
LLM CI

cc: @psiddh @shewu-quic @haowhsu-quic @winskuo-quic

Author: DannyYuyang-quic

examples/qualcomm/oss_scripts/llama/static_llm_quant_recipe.py

@@ -103,7 +103,7 @@ def __init__(self, verbose: bool = False):
                 granularity=QuantGranularity.PER_CHANNEL,
             )
             .add_regex(
-                {r"layers\..*\.attention\.wv.*"},
+                {r"layers\..*\.attention\..*wv.*"},
                 QuantDtype.use_8a4w,
                 False,
                 act_observer=MinMaxObserver,
@@ -150,7 +150,7 @@ def __init__(self, verbose: bool = False):
             .add_regex(
                 {
                     r"output\.conv",
-                    r"layers\.[0-3]\.feed_forward\.w2_conv",
+                    r"layers\.[0-3]\.feed_forward\..*w2_conv",
                 },
                 QuantDtype.use_16a8w,
                 False,
@@ -189,7 +189,7 @@ def __init__(self, verbose: bool = False):
             .add_regex(
                 {
                     r"output\.conv",
-                    r"layers\.2[1-7]\.feed_forward\.w2_conv",
+                    r"layers\.2[1-7]\.feed_forward\..*w2_conv",
                 },
                 QuantDtype.use_16a8w,
                 False,
@@ -249,7 +249,7 @@ def __init__(self, verbose: bool = False):
             )
             .add_regex(
                 {
-                    r"layers\..*\.attention\.wv.*",
+                    r"layers\..*\.attention\..*wv.*",
                     r"output\.conv",
                 },
                 QuantDtype.use_16a8w,
@@ -287,7 +287,7 @@ def __init__(self, verbose: bool = False):
             )
             .add_regex(
                 {
-                    r"layers\..*\.attention\.wv.*",
+                    r"layers\..*\.attention\..*wv.*",
                 },
                 QuantDtype.use_16a8w,
                 False,
@@ -324,7 +324,7 @@ def __init__(self, verbose: bool = False):
             )
             .add_regex(
                 {
-                    r"layers\..*\.attention\.wv.*",
+                    r"layers\..*\.attention\..*wv.*",
                 },
                 QuantDtype.use_16a8w,
                 False,
@@ -420,7 +420,7 @@ def __init__(self, verbose: bool = False):
             )
             .add_regex(
                 {
-                    r"layers\..*\.attention\.wv.*",
+                    r"layers\..*\.attention\..*wv.*",
                 },
                 QuantDtype.use_16a8w,
                 False,
@@ -457,9 +457,9 @@ def __init__(self, verbose: bool = False):
             )
             .add_regex(
                 {
-                    r"layers\..*\.attention\.wv.*",
-                    r"layers\..*\.feed_forward\.w3_conv",
-                    r"layers\..*\.feed_forward\.w2_conv",
+                    r"layers\..*\.attention\..*wv.*",
+                    r"layers\..*\.feed_forward\..*w3_conv",
+                    r"layers\..*\.feed_forward\..*w2_conv",
                     r"output\.conv",
                 },
                 QuantDtype.use_16a8w,
@@ -518,7 +518,7 @@ def __init__(self, verbose: bool = False):
                 extra_kwargs={"block_size": (1, 16, 1, 1)},
             )
             .add_regex(
-                {r"layers\..*\.attention\.wv.*"},
+                {r"layers\..*\.attention\..*wv.*"},
                 QuantDtype.use_8a4w,
                 False,
                 act_observer=MinMaxObserver,
@@ -620,7 +620,7 @@ def __init__(self, verbose: bool = False):
             )
             .add_regex(
                 {
-                    r"layers\..*\.feed_forward\.w2_conv",
+                    r"layers\..*\.feed_forward\..*w2_conv",
                 },
                 QuantDtype.use_16a8w,
                 False,
@@ -717,9 +717,9 @@ def __init__(self, verbose: bool = False):
             )
             .add_regex(
                 {
-                    r"layers\..*\.attention\.wq.*",
-                    r"layers\..*\.attention\.wk.*",
-                    r"layers\..*\.attention\.wv.*",
+                    r"layers\..*\.attention\..*wq.*",
+                    r"layers\..*\.attention\..*wk.*",
+                    r"layers\..*\.attention\..*wv.*",
                 },
                 QuantDtype.use_16a8w,
                 False,