Update

[ghstack-poisoned]

Author: shoumikhin

.github/workflows/_test_arduino_library.yml

@@ -89,4 +89,4 @@ jobs:
         cp ../../LICENSE arduino_lib/ExecuTorch/LICENSE
         cp README.md arduino_lib/ExecuTorch/README.md
         (cd arduino_lib/ExecuTorch && arduino-lint \
-          --project-type library --library-manager submit --compliance strict)
+          --project-type library --library-manager update --compliance strict)

.github/workflows/build-cmsis-pack.yml

@@ -22,7 +22,6 @@ on:
     paths:
       - .github/workflows/build-cmsis-pack.yml
       - backends/arm/cmsis_pack/**
-      - backends/arm/cmsis_pack/scripts/**
       - backends/arm/runtime/**
       - backends/cortex_m/**
       - kernels/portable/**
@@ -33,7 +32,6 @@ on:
     paths:
       - .github/workflows/build-cmsis-pack.yml
       - backends/arm/cmsis_pack/**
-      - backends/arm/cmsis_pack/scripts/**
   workflow_dispatch:
     inputs:
       version_override:
@@ -80,7 +78,9 @@ jobs:
         # Stage 1: Build core ExecuTorch with arm-none-eabi-gcc
         # This generates required headers (flatbuffers, schema)
         backends/arm/scripts/build_executorch.sh
-        CMAKE_BUILD_DIR="$(pwd)/cmake-out-arm"
+        # Must match build_executorch.sh's output dir (et_build_root/cmake-out);
+        # copy_sources.sh hard-fails if the generated schema headers are absent.
+        CMAKE_BUILD_DIR="$(pwd)/arm_test/cmake-out"
         echo "::endgroup::"
 
         echo "::group::Determine pack version"

.github/workflows/mlx.yml

@@ -14,6 +14,7 @@ on:
       - extension/llm/export/**
       - extension/audio/**
       - examples/models/gemma4_31b/**
+      - examples/models/muse-glimmer/**
       - examples/models/parakeet/**
       - examples/models/voxtral_realtime/**
       - examples/models/qwen3_5_moe/**
@@ -90,6 +91,7 @@ jobs:
           backends/mlx/test/test_slot_recycling.py \
           backends/mlx/test/test_sample.py \
           examples/models/gemma4_31b/tests/test_mlx_pipeline.py \
+          examples/models/muse-glimmer/tests/test_mlx_pipeline.py \
           -v
         echo "::endgroup::"
 
@@ -192,6 +194,52 @@ jobs:
         echo "Success: built $RUNNER"
         echo "::endgroup::"
 
+  # Build-only: the Muse Glimmer GGUF checkpoints are far too large to export in
+  # CI, so this covers the compile / link / metallib wiring of the runners --
+  # which is what MLX backend changes are most likely to break.
+  test-mlx-muse-glimmer-build:
+    needs: run-decision
+    if: |
+      github.event_name == 'pull_request' ||
+      needs.run-decision.outputs.is-full-run == 'true'
+    uses: pytorch/test-infra/.github/workflows/macos_job.yml@main
+    with:
+      default-packages: ""
+      job-name: test-mlx-muse-glimmer-build
+      runner: macos-14-xlarge
+      python-version: "3.12"
+      submodules: recursive
+      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+      timeout: 90
+      script: |
+        set -eux
+
+        echo "::group::Install ExecuTorch"
+        ${CONDA_RUN} python install_executorch.py > /dev/null
+        echo "::endgroup::"
+
+        ${CONDA_RUN} pip list
+
+        echo "::group::Build Muse Glimmer runners and worker with MLX"
+        ${CONDA_RUN} make muse-glimmer-mlx
+        BIN_DIR=cmake-out/examples/models/muse-glimmer
+        for bin in solo_runner dflash_runner muse_glimmer_worker; do
+          if [ ! -x "${BIN_DIR}/${bin}" ]; then
+            echo "Failed: ${bin} not found at ${BIN_DIR}/${bin}"
+            exit 1
+          fi
+        done
+        # Runtime kernel load falls back to an absolute build-tree path, so a
+        # missing colocated metallib only breaks a relocated binary. Assert the
+        # copy so the runners stay self-contained (needs EXECUTORCH_BUILD_MLX=ON
+        # in the preset, which drives executorch_target_copy_mlx_metallib).
+        if [ ! -f "${BIN_DIR}/mlx.metallib" ]; then
+          echo "Failed: mlx.metallib not copied next to the runners"
+          exit 1
+        fi
+        echo "Success: built solo_runner, dflash_runner and muse_glimmer_worker"
+        echo "::endgroup::"
+
   backend-tester:
     needs: run-decision
     if: |

Makefile

@@ -91,7 +91,7 @@
 #
 # ==============================================================================
 
-.PHONY: voxtral-cuda voxtral-cpu voxtral-metal voxtral-mlx voxtral_realtime-cuda voxtral_realtime-cpu voxtral_realtime-metal voxtral_realtime-mlx voxtral_tts-cpu voxtral_tts-cuda whisper-cuda whisper-cuda-debug whisper-cpu whisper-metal parakeet-cuda parakeet-cuda-debug parakeet-cpu parakeet-metal parakeet-mlx parakeet-vulkan dinov2-cuda dinov2-cuda-debug sortformer-cuda sortformer-cpu silero-vad-cpu llama-cuda llama-cuda-debug llama-cpu lfm_2_5-mlx llava-cpu gemma3-cuda gemma3-cpu gemma4_31b-cuda gemma4_31b-mlx muse-glimmer-cuda qwen3_5_moe-cuda qwen3_5_moe-metal qwen3_5_moe-mlx clean help
+.PHONY: voxtral-cuda voxtral-cpu voxtral-metal voxtral-mlx voxtral_realtime-cuda voxtral_realtime-cpu voxtral_realtime-metal voxtral_realtime-mlx voxtral_tts-cpu voxtral_tts-cuda whisper-cuda whisper-cuda-debug whisper-cpu whisper-metal parakeet-cuda parakeet-cuda-debug parakeet-cpu parakeet-metal parakeet-mlx parakeet-vulkan dinov2-cuda dinov2-cuda-debug sortformer-cuda sortformer-cpu silero-vad-cpu llama-cuda llama-cuda-debug llama-cpu lfm_2_5-mlx llava-cpu gemma3-cuda gemma3-cpu gemma4_31b-cuda gemma4_31b-mlx muse-glimmer-cuda muse-glimmer-mlx qwen3_5_moe-cuda qwen3_5_moe-metal qwen3_5_moe-mlx clean help
 
 help:
 	@echo "This Makefile adds targets to build runners for various models on various backends. Run using \`make <target>\`. Available targets:"
@@ -130,6 +130,7 @@ help:
 	@echo "  gemma4_31b-cuda     - Build Gemma 4 31B runner and worker with CUDA backend"
 	@echo "  gemma4_31b-mlx      - Build Gemma 4 31B runner and worker with MLX backend"
 	@echo "  muse-glimmer-cuda   - Build Muse Glimmer runners and worker with CUDA backend"
+	@echo "  muse-glimmer-mlx    - Build Muse Glimmer runners and worker with MLX backend"
 	@echo "  qwen3_5_moe-cuda    - Build Qwen3.5 MoE runner with CUDA backend"
 	@echo "  qwen3_5_moe-metal   - Build Qwen3.5 MoE runner with Metal backend"
 	@echo "  qwen3_5_moe-mlx     - Build Qwen3.5 MoE runner with MLX backend"
@@ -453,6 +454,17 @@ muse-glimmer-cuda:
 	@echo "  DFlash runner: cmake-out/examples/models/muse-glimmer/dflash_runner"
 	@echo "  Worker:        cmake-out/examples/models/muse-glimmer/muse_glimmer_worker"
 
+muse-glimmer-mlx:
+	@echo "==> Building and installing ExecuTorch with MLX..."
+	cmake --workflow --preset mlx-release
+	@echo "==> Building Muse Glimmer runners and worker with MLX..."
+	cd examples/models/muse-glimmer && cmake --workflow --preset muse-glimmer-mlx
+	@echo ""
+	@echo "✓ Build complete!"
+	@echo "  Solo runner:   cmake-out/examples/models/muse-glimmer/solo_runner"
+	@echo "  DFlash runner: cmake-out/examples/models/muse-glimmer/dflash_runner"
+	@echo "  Worker:        cmake-out/examples/models/muse-glimmer/muse_glimmer_worker"
+
 gemma4_31b-cuda:
 	@echo "==> Building and installing ExecuTorch with CUDA..."
 	cmake --workflow --preset llm-release-cuda

backends/arm/_passes/fold_qdq_with_annotated_qparams_pass.py

@@ -405,11 +405,13 @@ def call(self, graph_module: GraphModule) -> PassResult:  # noqa: C901
 
             input_qparams: dict[int, QuantArgs] = {}
             input_nodes_to_remove: dict[int, set[Node]] = {}
+            input_nodes_seen: set[Node] = set()
             for i, arg in enumerate(n.args):
                 qparams, nodes_to_remove = self._extract_arg_input_params(arg)
                 if qparams is not None:
                     input_qparams[i] = qparams
-                    input_nodes_to_remove[i] = nodes_to_remove
+                    input_nodes_to_remove[i] = nodes_to_remove - input_nodes_seen
+                    input_nodes_seen.update(nodes_to_remove)
 
             preserve_qdq = self._has_partial_binary_tensor_qdq_inputs(n, input_qparams)
             graph_modified = graph_modified or not preserve_qdq

backends/arm/cmsis_pack/contributions/add/Documentation/README.md

@@ -28,10 +28,12 @@ This pack provides:
      - component: Machine Learning:ExecuTorch:Runtime
      - component: Machine Learning:ExecuTorch:Kernel Utils
 
-     # Backend (choose one or more)
-     - component: Machine Learning:ExecuTorch:Backend::EthosU
+     # Backend (choose one or more). CMSIS component IDs use a single
+     # colon between Cclass / Cgroup / Csub, with a space (not "::")
+     # inside the Csub name.
+     - component: Machine Learning:ExecuTorch:Backend EthosU
      # or
-     - component: Machine Learning:ExecuTorch:Backend::CortexM
+     - component: Machine Learning:ExecuTorch:Backend CortexM
    ```
 
 3. Include ExecuTorch headers in your code:

backends/arm/cmsis_pack/scripts/build_pack.sh

@@ -107,18 +107,21 @@ cd "$PACK_BUILD"
 if command -v zip &> /dev/null; then
     zip -r "$PACK_FILE" . -x "*.DS_Store" -x ".git*" -x "*/generated/*" -x "*.py"
 else
-    python3 -c "
-import zipfile, os
-with zipfile.ZipFile('$PACK_FILE', 'w', zipfile.ZIP_DEFLATED) as zf:
+    # Pass $PACK_FILE as sys.argv[1] so the path is safe against
+    # shell-special characters (single quotes in particular).
+    python3 - "$PACK_FILE" <<'PYEOF'
+import sys, zipfile, os
+pack_file = sys.argv[1]
+with zipfile.ZipFile(pack_file, 'w', zipfile.ZIP_DEFLATED) as zf:
     for root, dirs, files in os.walk('.'):
         dirs[:] = [d for d in dirs if not d.startswith('.') and d != 'generated']
         for f in files:
             if f.startswith('.') or f == '.DS_Store' or f.endswith('.py'):
                 continue
             p = os.path.join(root, f)
             zf.write(p, os.path.relpath(p, '.'))
-print(f'Created: $PACK_FILE')
-"
+print(f'Created: {pack_file}')
+PYEOF
 fi
 
 echo ""

backends/arm/cmsis_pack/scripts/copy_sources.sh

@@ -14,7 +14,7 @@
 # Usage:
 #   ./copy_sources.sh --executorch-root <path> --build-dir <path> \
 #                     --pack-staging <path>
-set -e
+set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 PACK_DIR="$(cd "$SCRIPT_DIR/../../cmsis_pack" && pwd)"
@@ -115,7 +115,7 @@ cp -r "${PACK_SRC}/src/kernels" "${PACK_SRC}/include/executorch/"
 
 echo "  Copying extension sources..."
 mkdir -p "${PACK_SRC}/src/extension"
-for d in data_loader memory_allocator runner_util; do
+for d in data_loader memory_allocator runner_util tensor; do
     if [[ -d "${EXECUTORCH_ROOT}/extension/$d" ]]; then
         cp -r "${EXECUTORCH_ROOT}/extension/$d" "${PACK_SRC}/src/extension/"
     fi
@@ -138,6 +138,18 @@ for candidate in \
         break
     fi
 done
+# A pack without the generated flatbuffers schema headers compiles nothing:
+# every consumer fails at executorch/schema/program_generated.h. Fail here
+# rather than shipping a broken archive.
+for required in program_generated.h scalar_type_generated.h; do
+    if [[ ! -f "${PACK_SRC}/src/schema/${required}" ]]; then
+        echo "ERROR: ${required} not found in the CMake build tree." >&2
+        echo "  Looked in: ${BUILD_DIR}/schema/include/executorch/schema" >&2
+        echo "  Run the ExecuTorch CMake configure+build first so BUILD_DIR" >&2
+        echo "  contains the generated schema headers (see build_pack.sh -h)." >&2
+        exit 1
+    fi
+done
 cp -r "${PACK_SRC}/src/schema" "${PACK_SRC}/include/executorch/"
 
 echo "  Copying generated flatbuffers headers..."
@@ -150,14 +162,27 @@ for candidate in \
         break
     fi
 done
+# Same rule as the schema headers: the pack bundles flatbuffers/, and the
+# runtime does not compile without it. Refuse to produce a pack missing it.
+if [[ ! -f "${PACK_SRC}/include/flatbuffers/flatbuffers.h" ]]; then
+    echo "ERROR: flatbuffers headers not found in the CMake build tree." >&2
+    echo "  Looked in: ${BUILD_DIR}/third-party/{flatbuffers,flatc_ep}/include" >&2
+    echo "  Run the ExecuTorch CMake configure+build first so BUILD_DIR" >&2
+    echo "  contains the flatc external-project headers." >&2
+    exit 1
+fi
 
-# Flatbuffers headers are redistributed inside the pack; ship the
-# upstream Apache-2.0 LICENSE alongside per its terms.
-if [[ -f "${EXECUTORCH_ROOT}/third-party/flatbuffers/LICENSE" ]] \
-   && [[ -d "${PACK_SRC}/include/flatbuffers" ]]; then
-    cp "${EXECUTORCH_ROOT}/third-party/flatbuffers/LICENSE" \
-       "${PACK_SRC}/include/flatbuffers/LICENSE"
+# Flatbuffers headers are redistributed inside the pack, so shipping the
+# upstream Apache-2.0 LICENSE alongside them is a condition of that
+# redistribution -- a pack without it must not be published.
+if [[ ! -f "${EXECUTORCH_ROOT}/third-party/flatbuffers/LICENSE" ]]; then
+    echo "ERROR: third-party/flatbuffers/LICENSE not found in the source tree." >&2
+    echo "  The pack redistributes the flatbuffers headers and must ship" >&2
+    echo "  their licence. Run: git submodule update --init third-party/flatbuffers" >&2
+    exit 1
 fi
+cp "${EXECUTORCH_ROOT}/third-party/flatbuffers/LICENSE" \
+   "${PACK_SRC}/include/flatbuffers/LICENSE"
 
 echo "  Creating c10 and torch include paths..."
 C10_DIR="${PACK_SRC}/src/runtime/core/portable_type/c10/c10"