SkillsAdd

pytorch/executorch · Archived

qualcomm

Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend. Use when working on backends/qualcomm/, building QNN (use backends/qualcomm/scripts/build.sh), adding new ops or passes, running QNN delegate tests, or exporting models for Qualcomm HTP/GPU targets. Also exposes a Buck-vs-CMake parity workflow — invoke as `/qualcomm buck-fix`, `/qualcomm buck-cmake fix`, `/qualcomm buck-parity`, or any user request to fix `test-qnn-buck-build-linux` CI failures or check buck/cmake drift in bac…

First seen Jul 3, 2026

Installation

$ npx skills add pytorch/executorch --skill qualcomm
View on skills.sh ↗ GitHub repository ↗

Summary

  • Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend.
  • Use when working on backends/qualcomm/, building QNN (use backends/qualcomm/scripts/build.sh), adding new ops or passes, running QNN delegate tests, or exporting models for Qualcomm HTP/GPU targets.
  • Also exposes a Buck-vs-CMake parity workflow — invoke as `/qualcomm buck-fix`, `/qualcomm buck-cmake fix`, `/qualcomm buck-parity`, or any user request to fix `test-qnn-buck-build-linux` CI failures or check buck/cmake drift in backends/qualcomm/.
  • Also covers QNN intermediate-output / per-layer accuracy debugging — trigger on phrases like "QNN accuracy issue", "QNN output doesn't match CPU", "debug per-layer for QNN", "find which QNN layer is wrong".

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

profile Same source
pytorch/executorch

Profile ExecuTorch model execution. Use when measuring performance, analyzing operator timing, …

6 installs
executorch-kb Same source
pytorch/executorch

Search the ExecuTorch tribal knowledge base covering QNN, XNNPACK, Vulkan, CoreML, Arm, and Cad…

6 installs
binary-size Same source
pytorch/executorch

Analyze and reduce ExecuTorch binary size. Use when investigating binary size, running size tes…

6 installs
building Same source
pytorch/executorch

Build ExecuTorch from source — Python package, C++ runtime, runners, cross-compilation, and bac…

5 installs

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

agent-browser Shared topics
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

810.4K installs
supabase-postgres-best-practices Shared topics
supabase/agent-skills

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill …

391.6K installs
vercel-react-best-practices Shared topics
vercel-labs/agent-skills 697.8K installs
web-design-guidelines Shared topics
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

617.3K installs
microsoft-foundry Shared topics
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

576.5K installs
azure-diagnostics Shared topics
microsoft/azure-skills

Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe …

568.9K installs

Also in this package

Other skills from pytorch/executorch.

npx skills add pytorch/executorch
profile 6 executorch-kb 6 binary-size 6 building 5 zephyr 5 setup 5 export 5 cortex-m 5

Browse all from pytorch/executorch

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Also listed on

Alternate registries and mirrors of this skill.

Repository health

Stars 5.0K
License LICENSE
Default branch main
Open issues 930
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 6,058 B
  • docs SUMMARY.md 742 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 6 installs

SKILL.md

QNN (Qualcomm AI Engine Direct) Backend

Slash command argument routing

When this skill is invoked with arguments (e.g. /qualcomm <args>), classify the args FIRST and route before doing anything else:

If args contain any of… Route to
buck-fix, buck-cmake, buck cmake, buck-parity, buck parity, buck ci, qnn buck, fix qnn ci, test-qnn-buck-build-linux, or any natural-language request to fix QNN buck CI / catch buck-cmake drift Read buck_parity.md and follow it end-to-end. Default mode: full iterative-fix loop. If the args also contain check or diagnose, run buck once and report only — do not apply fixes.
(no args) or any other args Stay in this file; treat as a normal /qualcomm discovery request and use the Advanced Topics table below.

Advanced Topics

When the user's request falls into one of these areas, read the corresponding file before proceeding:

Topic File When to read
Export / lowering / quantization options / pass pipelines lowering_export.md User asks about exporting, lowering, quantization config, QuantDtype, QuantRecipe, pass pipelines
New op development newopdevelopment.md User asks to add/implement a new op or op builder
Model enablement model_enablement.md User asks to enable a new model end-to-end
Buck vs CMake parity (pre-PR or fix red CI) buck_parity.md User changed BUCK / TARGETS / targets.bzl or CMakeLists.txt under backends/qualcomm/, added new .cpp / .h / #include there, is preparing to push a PR that touches QNN, or the test-qnn-buck-build-linux CI check on their PR is red and they want to fix it locally. Direct trigger: /qualcomm buck-fix.
Profiling & debugging profiling.md User asks about profiling, optrace, QHAS, QAIRT Visualizer (file TBD)
QNN intermediate-output / per-layer accuracy debugging qnnintermediatedebugger.md User reports QNN-vs-CPU accuracy divergence, asks to debug per-layer / intermediate output for QNN, mentions QNNIntermediateDebugger / QcomNumericalComparator, or wants to find which layer causes a QNN accuracy drop. Workflow generates a new debug script from the user's existing example script.

Building

Use backends/qualcomm/scripts/build.sh. Linux only (macOS not supported).

Environment variables:

  • QNNSDKROOT — path to QNN SDK (auto-downloaded if not set)
  • ANDROIDNDKROOT — path to Android NDK (auto-downloaded if not set)

Build targets:

Target Default Build dir
x86_64 (Python interface + host tools) enabled build-x86/
Android arm64-v8a (device runner) enabled build-android/
Direct mode (LPAI ADSP or Hexagon CDSP) disabled build-direct/
OE Linux embedded disabled build-oe-linux/

Common build commands:

# Full build (x86_64 + Android)
./backends/qualcomm/scripts/build.sh

# x86_64 only (faster, for Python interface development)
./backends/qualcomm/scripts/build.sh --skip_linux_android

# Android only (skip x86_64)
./backends/qualcomm/scripts/build.sh --skip_x86_64

# Incremental build (skip clean)
./backends/qualcomm/scripts/build.sh --no_clean

# Enable Hexagon DSP direct mode (requires HEXAGON_SDK_ROOT, HEXAGON_TOOLS_ROOT, DSP_VERSION)
./backends/qualcomm/scripts/build.sh --enable_hexagon

# OE Linux embedded target (requires TOOLCHAIN_ROOT_HOST, TOOLCHAIN_ROOT_TARGET)
./backends/qualcomm/scripts/build.sh --enable_linux_embedded

# Release build
./backends/qualcomm/scripts/build.sh --release

# Control parallelism
./backends/qualcomm/scripts/build.sh --job_number 8

After x86_64 build, the Python interface .so files are copied to backends/qualcomm/python/ automatically.

Testing

QNN_SDK_ROOT=/path/to/qnn_sdk \
ANDROID_NDK_ROOT=/path/to/android_ndk \
LD_LIBRARY_PATH=/path/to/executorch/build-x86/lib:/path/to/qnn_sdk/lib/x86_64-linux-clang \
PYTHONPATH=$(dirname $EXECUTORCH_ROOT) \
python backends/qualcomm/tests/test_qnn_delegate.py \
    TestQNNFloatingPointOperator.test_qnn_backend_abs \
    --host $HOST --device $DEVICE_SERIAL --soc_model SM8850 --build_folder build-android -a /path/to/artifacts

Note (build from source): Set PYTHONPATH to the parent directory of the executorch repo root. Required because executorch.examples.qualcomm lives in the source tree and is not installed into site-packages.

Required flags: --socmodel (SoC model), --buildfolder (Android build dir). Optional: --device (device serial), --host (host), -a (artifact dir), --compileonly, --enablex86_64.

Test classes:

Class Description
TestQNNFloatingPointOperator FP16 operator tests
TestQNNQuantizedOperator Quantized operator tests
TestQNNFloatingPointModel FP16 model-level tests
TestQNNQuantizedModel Quantized model-level tests
TestQNNFloatingPointUtils FP16 utility tests
TestQNNQuantizedUtils Quantized utility tests
TestExampleLLMScript LLM script tests
TestExampleMultimodalityScript Multimodality script tests
TestExampleOssScript OSS model script tests
TestExampleScript General example script tests
TestUtilsScript Utility script tests