Qualcomm AI Engine Direct - fix extra argument in static Mimi decoder call

[Anai-Guo]

Problem

examples/qualcomm/oss_scripts/moshi/mimi.py defines the static decoder helper with five parameters:

def inference_static_mimi_decoder(
    args,
    qnn_config,
    encoded_results,
    pcm_chunk_size,
    static_decoder_pte_filename,
):

There are two call sites. The --pre_gen_pte branch (line 400) is correct, but the
default compile-and-run branch (line 416) inserts encoded_results_list as a fourth
positional argument:

qnn_decode_res = inference_static_mimi_decoder(
    args,
    qnn_config,
    encoded_results,
    encoded_results_list,   # <-- not a parameter
    pcm_chunk_size,
    static_decoder_pte_filename,
)

so running the script without --compile_only / --pre_gen_pte — the normal path —
fails at decode time with:

TypeError: inference_static_mimi_decoder() takes 5 positional arguments but 6 were given

Why the argument is dropped rather than added as a parameter

encoded_results_list is a newline-joined "input_N_0.raw" listing built in
export_mimi_decoder. It has no consumer:

• inference_static_mimi_decoder builds its own runner_cmd (--model_path,
  --output_folder_path) with no input-list flag;
• it pushes with adb.push(inputs=encoded_results), and SimpleADB.push
  (backends/qualcomm/export_utils.py) has signature
  push(self, inputs=None, files=None, backends=None, init_env=True) — no
  input-list parameter;
• every other QNN OSS script likewise calls adb.push(inputs=inputs).

encoded_results_list is referenced nowhere else in the file, so this PR removes the
stray argument together with the two lines that build the now-unused string. The
encoded_results[index] = encoder_result.to(torch.int32) conversion in the same loop
is kept.

Verification

Signature replay against main (4ce2ec2):

[BEFORE] signature: (args, qnn_config, encoded_results, pcm_chunk_size, static_decoder_pte_filename)
  line 400: 5 args -> OK
  line 416: 6 args -> TypeError: too many positional arguments

[AFTER]  signature: (args, qnn_config, encoded_results, pcm_chunk_size, static_decoder_pte_filename)
  line 398: 5 args -> OK
  line 414: 5 args -> OK

Diff is three deleted lines; no behavior other than the crash changes.

🤖 Generated with Claude Code

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22586

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

⚠️ 20 Awaiting Approval

As of commit 6d35fbb with merge base 4ce2ec2 ():

AWAITING APPROVAL - The following workflows need approval before CI can run:

• Build Aarch64 Linux CUDA Wheels (gh)
• Build Aarch64 Linux Wheels (gh)
• Build documentation (gh)
• Build Linux CUDA Wheels (gh)
• Build Linux Wheels (gh)
• Build macOS Wheels (gh)
• Build Presets (gh)
• Build Windows Wheels (gh)
• Lint (gh)
• periodic (gh)
• pull (gh)
• Test ARM Backend (gh)
• Test CoreML Backend (gh)
• Test Cortex-M Backend (gh)
• Test NXP Backend (gh)
• Test QNN Backend (gh)
• Test QNN Windows MSVC build (gh)
• Test Vulkan Backend (gh)
• Test WebGPU Backend (gh)
• Test XNNPACK Backend (gh)

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[linux-foundation-easycla]

• ❌ - login: @Anai-Guo / name: Tai An. The commit (6d35fbb) is not authorized under a signed CLA. Please click here to be authorized. For further assistance with EasyCLA, please visit our EasyCLA portal and chat with our support bot.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.