…RV-Headers patch

The previous baseline 945210e5 shipped ports/ggml-speech/patches/
0001-ggml-vulkan-find-spirv-headers.patch authored against speech tip
c9126afc. PR #14's mul_mat_vec / Adreno guards (also on this test
branch) added a Qualcomm-gated 'liblog' link block between Vulkan
target_link_libraries and target_include_directories in
src/ggml-vulkan/CMakeLists.txt, breaking the patch's hunk-2 context.

Registry branch QVAC-19254-android-devicefarm-test was amended +
force-pushed with a regenerated patch whose hunk-2 context matches
the PR-#14 layout. Tree-SHA of ports/ggml-speech updates from
e941a423... -> 381370e3...; baseline.json + versions/g- updated to
match.

QVAC-19254

… Device Farm Adreno smoke

The Device Farm Chatterbox GPU smoke test (un-quarantined in the prior
commit) showed backendDevice=0 / backendId=0 (CPU) on Samsung S25 Ultra
+ Pixel 9 even with useGPU=true. Logcat traced it to the
ChatterboxModel::loadLocked() #ifdef __ANDROID__ block that
unconditionally forces useGpu=false before tts_cpp::chatterbox::Engine
is constructed -- so tts-cpp's init_gpu_backend (with PR #14 + PR #15
fixes) is never exercised on Android.

Lifting the guard on the test branch so the AWS Device Farm Adreno smoke
can validate the PR #14 (Vulkan-Adreno guards) and PR #15 (OpenCL
elementwise kernels) paths end-to-end. The symmetric SupertonicModel
guard stays in place (out of scope; Supertonic GPU smoke currently
passes via JS-layer rejection on the test's invalid model path).

[DO NOT MERGE] branch only.

QVAC-19254

…st branch + un-quarantine Adreno GPU smoke for Device Farm validation

Bumps the tts-ggml default-registry baseline to
tetherto/qvac-registry-vcpkg@945210e (QVAC-19254-android-devicefarm-test
branch), which pins:
  - ggml-speech port REF -> tetherto/qvac-ext-ggml@2bb83370 (combined
    test branch with PR #14 Vulkan-Adreno guards + PR #15 OpenCL
    elementwise kernels on top of speech tip c9126afc / v0.10.2)
  - tts-cpp port REF -> tetherto/qvac-ext-lib-whisper.cpp@afe2fd21
    (PR #35 head: Adreno backend tier policy)

Adds spirv-headers to the microsoft/vcpkg registry packages array so
ggml-speech's vulkan-feature dependency resolves (mirrors what
transcription-whispercpp already does for the whisper-cpp port).

Removes the Android short-circuit in the Chatterbox GPU smoke test so
the AWS Device Farm Adreno 740 pool actually exercises the GPU path.
Without the still-uncommitted ggml-opencl device_description fix, the
tts-cpp tier policy may pick Vulkan on Adreno; PR #14's Qualcomm-gated
guards are the safety net being validated in that path. PR #15's
OpenCL kernels are exercised only if the policy picks OpenCL.

Revert this branch once PR #14 / PR #15 / PR #35 land on their
respective default branches and a registry bump captures the merged
state.

QVAC-19254

…RV-Headers patch

The previous baseline 945210e5 shipped ports/ggml-speech/patches/
0001-ggml-vulkan-find-spirv-headers.patch authored against speech tip
c9126afc. PR #14's mul_mat_vec / Adreno guards (also on this test
branch) added a Qualcomm-gated 'liblog' link block between Vulkan
target_link_libraries and target_include_directories in
src/ggml-vulkan/CMakeLists.txt, breaking the patch's hunk-2 context.

Registry branch QVAC-19254-android-devicefarm-test was amended +
force-pushed with a regenerated patch whose hunk-2 context matches
the PR-#14 layout. Tree-SHA of ports/ggml-speech updates from
e941a423... -> 381370e3...; baseline.json + versions/g- updated to
match.

QVAC-19254

… Device Farm Adreno smoke

The Device Farm Chatterbox GPU smoke test (un-quarantined in the prior
commit) showed backendDevice=0 / backendId=0 (CPU) on Samsung S25 Ultra
+ Pixel 9 even with useGPU=true. Logcat traced it to the
ChatterboxModel::loadLocked() #ifdef __ANDROID__ block that
unconditionally forces useGpu=false before tts_cpp::chatterbox::Engine
is constructed -- so tts-cpp's init_gpu_backend (with PR #14 + PR #15
fixes) is never exercised on Android.

Lifting the guard on the test branch so the AWS Device Farm Adreno smoke
can validate the PR #14 (Vulkan-Adreno guards) and PR #15 (OpenCL
elementwise kernels) paths end-to-end. The symmetric SupertonicModel
guard stays in place (out of scope; Supertonic GPU smoke currently
passes via JS-layer rejection on the test's invalid model path).

[DO NOT MERGE] branch only.

QVAC-19254

…ve init_gpu_backend try-catch

Previous Device Farm run validated Samsung Galaxy S25 Ultra (Adreno 830)
end-to-end -- Chatterbox GPU smoke PASSED 3/3 with OpenCL backend
selected via PR #15 kernels. Google Pixel 9 Pro XL (Tensor G4 / Mali)
SIGABRT-crashed during Vulkan-on-Mali pipeline init (Mali outside the
Qualcomm-vendor gate that PR #14 covers).

Bumps the registry baseline to the test branch tip that pins tts-cpp
port REF to whisper.cpp@3613786b (PR #35 head + one defensive commit).
The new commit wraps ggml_backend_dev_init in try-catch inside
init_gpu_backend's try_init lambda so an unhandled C++ exception
thrown by an unsupported GPU's backend init no longer terminates the
host process -- the policy now falls through to the next bucket and
ultimately to CPU. Expected outcome on the next Device Farm run:
Pixel runs to completion (Chatterbox engine reports CPU); test still
asserts GPU on Android so the assertion fails cleanly without crash.

QVAC-19254

…p registry test-branch pin)

Replace the default-registry test-branch reference (QVAC-19254-android-devicefarm-test) with overlay-ports copied straight into the PR, so the exact tts-cpp / ggml-speech sources under test are visible here without the registry indirection (reviewer feedback). default-registry reverts to the production baseline 74d2dfd0 (no baseline advance).

tts-cpp overlay -> qvac-ext-lib-whisper.cpp PR #36 @ 5205428e; ggml-speech overlay -> qvac-ext-ggml PR #14 + #17 @ 2bb83370.

…st branch + un-quarantine Adreno GPU smoke for Device Farm validation

Bumps the tts-ggml default-registry baseline to
tetherto/qvac-registry-vcpkg@945210e (QVAC-19254-android-devicefarm-test
branch), which pins:
  - ggml-speech port REF -> tetherto/qvac-ext-ggml@2bb83370 (combined
    test branch with PR #14 Vulkan-Adreno guards + PR #15 OpenCL
    elementwise kernels on top of speech tip c9126afc / v0.10.2)
  - tts-cpp port REF -> tetherto/qvac-ext-lib-whisper.cpp@afe2fd21
    (PR #35 head: Adreno backend tier policy)

Adds spirv-headers to the microsoft/vcpkg registry packages array so
ggml-speech's vulkan-feature dependency resolves (mirrors what
transcription-whispercpp already does for the whisper-cpp port).

Removes the Android short-circuit in the Chatterbox GPU smoke test so
the AWS Device Farm Adreno 740 pool actually exercises the GPU path.
Without the still-uncommitted ggml-opencl device_description fix, the
tts-cpp tier policy may pick Vulkan on Adreno; PR #14's Qualcomm-gated
guards are the safety net being validated in that path. PR #15's
OpenCL kernels are exercised only if the policy picks OpenCL.

Revert this branch once PR #14 / PR #15 / PR #35 land on their
respective default branches and a registry bump captures the merged
state.

QVAC-19254

…RV-Headers patch

The previous baseline 945210e5 shipped ports/ggml-speech/patches/
0001-ggml-vulkan-find-spirv-headers.patch authored against speech tip
c9126afc. PR #14's mul_mat_vec / Adreno guards (also on this test
branch) added a Qualcomm-gated 'liblog' link block between Vulkan
target_link_libraries and target_include_directories in
src/ggml-vulkan/CMakeLists.txt, breaking the patch's hunk-2 context.

Registry branch QVAC-19254-android-devicefarm-test was amended +
force-pushed with a regenerated patch whose hunk-2 context matches
the PR-#14 layout. Tree-SHA of ports/ggml-speech updates from
e941a423... -> 381370e3...; baseline.json + versions/g- updated to
match.

QVAC-19254

… Device Farm Adreno smoke

The Device Farm Chatterbox GPU smoke test (un-quarantined in the prior
commit) showed backendDevice=0 / backendId=0 (CPU) on Samsung S25 Ultra
+ Pixel 9 even with useGPU=true. Logcat traced it to the
ChatterboxModel::loadLocked() #ifdef __ANDROID__ block that
unconditionally forces useGpu=false before tts_cpp::chatterbox::Engine
is constructed -- so tts-cpp's init_gpu_backend (with PR #14 + PR #15
fixes) is never exercised on Android.

Lifting the guard on the test branch so the AWS Device Farm Adreno smoke
can validate the PR #14 (Vulkan-Adreno guards) and PR #15 (OpenCL
elementwise kernels) paths end-to-end. The symmetric SupertonicModel
guard stays in place (out of scope; Supertonic GPU smoke currently
passes via JS-layer rejection on the test's invalid model path).

[DO NOT MERGE] branch only.

QVAC-19254

…p registry test-branch pin)

Replace the default-registry test-branch reference (QVAC-19254-android-devicefarm-test) with overlay-ports copied straight into the PR, so the exact tts-cpp / ggml-speech sources under test are visible here without the registry indirection (reviewer feedback). default-registry reverts to the production baseline 74d2dfd0 (no baseline advance).

tts-cpp overlay -> qvac-ext-lib-whisper.cpp PR #36 @ 5205428e; ggml-speech overlay -> qvac-ext-ggml PR #14 + #17 @ 2bb83370.

…(PR #17 review fixes)

Point the ggml-speech overlay-port at the PR #17 branch head (speech v0.10.2 sync + ggml-opencl elementwise kernels for Chatterbox S3Gen + the PR #17 review fixes). Note: this drops the PR #14 (ggml-vulkan Adreno 740 / Qualcomm) commits that the prior 2bb83370 pin carried.

…-only source

The overlay's 0001-ggml-vulkan-find-spirv-headers.patch was contexted against PR #14's ggml-vulkan/CMakeLists.txt change (the Android log-link block), so it did not apply on the PR #17-only source (8de98a43) -> the vulkan-feature build failed on Linux/Android/Windows. Re-context hunk 2 onto plain PR #17 (target_include_directories) so the spirv-headers build glue applies independently of PR #14. Verified with 'git apply --check' against 8de98a43.

…test

Overlay-pins ggml-speech to qvac-ext-ggml PR #14 (commit 8bf760f4 -- Adreno
Vulkan support + the Parakeet quantized-matmul fix) and forces the Parakeet
Android tests onto Vulkan, to validate on Device Farm (Samsung S25 Ultra /
Adreno + Pixel 9 / Mali) that Vulkan runs Parakeet correctly and nothing else
breaks. NOT for merge -- the overlay + GPU-guard removal are test-only.

- vcpkg-overlay-ports/ggml-speech: pinned to qvac-ext-ggml@8bf760f4; Android
  default-features drop OpenCL (Vulkan-only) so the loader has no OpenCL .so
  and the tier policy selects Vulkan on Adreno.
- vcpkg-configuration.json: register ./vcpkg-overlay-ports.
- vcpkg.json: Android parakeet-cpp features=["vulkan"] + default-features:false.
- ParakeetModel.cpp: remove the Android useGPU=false guard so useGPU=true
  reaches the engine.
- mobile-perf-runner.js: assert Android use_gpu runs select Vulkan (backendId=3).

…gml (9be02126)

Point the device-farm overlay at qvac-ext-ggml@QVAC-19214-mali-rca (9be02126 =
PR #14's 8bf760f4 + a ggml_abort->logcat diagnostic). The Vulkan backend's
GGML_ASSERT on Mali-G715 is otherwise invisible: bare drops native stderr and
the addon abort callback never fires for the dlopen'd backend (separate linker
namespace). This rebuilds ggml-speech from the instrumented commit so the next
Device-Farm Mali EOU crash logs the exact assert under logcat tag ggml_abort.

…#14 commit, no RCA instrumentation)

Validate the tts-cpp Adreno-Vulkan fixes (Supertonic + Chatterbox) on the AWS
Device Farm via overlay ports, before the upstream PRs merge:

- vcpkg-overlay-ports/ggml-speech -> qvac-ext-ggml PR #14 (e6578d01)
- vcpkg-overlay-ports/tts-cpp     -> qvac-ext-lib-whisper.cpp PR #41 (bc872dd7)
- both overlays drop the Android OpenCL default-feature, and vcpkg.json forces
  tts-cpp[vulkan] (default-features:false) on Android -> the Adreno run uses Vulkan
- ChatterboxModel: remove the Android useGPU=false force-CPU guard
- gpu-smoke.test.js: un-skip the Chatterbox Android GPU smoke and assert the
  Android backendId is Vulkan (3), not OpenCL (4) or CPU

DO NOT MERGE: device-farm validation vehicle only.