cccclai

> Because we use MHA in source model level at AOT, the number of KV cache will be n_layers * [b, n_heads, cache_len, head_dim]. [And then we insert slice op...

Hey can you help rebasing? Trying to check the internal signal

There are some internal errors, can you fix with the patch below? ``` diff --git a/executorch/backends/qualcomm/tests/TARGETS b/executorch/backends/qualcomm/tests/TARGETS --- a/executorch/backends/qualcomm/tests/TARGETS +++ b/executorch/backends/qualcomm/tests/TARGETS @@ -58,6 +58,10 @@ "//caffe2:torch", "//executorch/exir:lib", "//executorch/backends/qualcomm/_passes:passes", + "//executorch/backends/qualcomm/partition:partition",...

Seems like missing some dependency ``` ModuleNotFoundError: No module named 'pydot' ``` Do you want to introduce this dependency in general?

Thank you for enable this feature and the detailed documentation! Just minor comments, can we move `examples/qualcomm/devtools/qnn_intermediate_debugger_demo.py` to `examples/qualcomm/devtools/qnn_intermediate_debugger_demo.py` just a bit clear on the content inside the folder

It seems like I merge some PRs that have conflict with this PR...can you rebase again?

There are some internal errors, I need to send a patch

Can you apply these changes ``` --- a/executorch/backends/qualcomm/debugger/TARGETS +++ b/executorch/backends/qualcomm/debugger/TARGETS @@ -10,3 +10,21 @@ "fbsource//third-party/pypi/pandas:pandas", ] ) + +runtime.python_library( + name = "qnn_intermediate_debugger", + srcs = [ + "format_outputs.py", +...

@abhinaykukkadapu this PR is different than the export recipe you added. It's about how to add more customization to quantize a model. The current recipe for different backends doesn't offer...

It seems like this PR break a unit test https://github.com/pytorch/executorch/actions/runs/19558624238/job/56006215617 can you fix it?