QVAC-3127: Updated port qvac-lib-inference-addon-cpp to v0.6.1 by jpgaribotti · Pull Request #13 · tetherto/qvac-registry-vcpkg

jpgaribotti · 2025-07-09T14:59:40Z

No description provided.

…18993) Re-pins the ggml-speech port from tetherto/qvac-ext-ggml @ 9562ed04 (2026-05-18, port-version 2 just landed in tetherto#156) to Zbig9000/qvac-ext-ggml @ 45dbdecd (2026-05-19, HEAD of QVAC-18992 PR tetherto#13). The new REF is a superset of 9562ed04: - 9562ed04 (GustavoA1604, PR tetherto#11) ggml-backend: android per-arch CPU variant dlopen fallback --- already on tetherto/speech - 19eac6f0 (ggml-org) sync up to ggml-org v0.10.2 (137 commits, bundled-ggml pin matching whisper.cpp v1.8.4.3's sync-ggml.last) - 4 conflict-resolution union merges in src/ggml-metal/ (additive, speech-stack patches + upstream's new GGML_OP_ROLL) --- details in tetherto/qvac-ext-ggml PR tetherto#13 TEMPORARY: REPO stays pinned at Zbig9000 fork until PR tetherto#13 lands on tetherto/speech. After that, flip REPO -> tetherto/qvac-ext-ggml + recompute SHA512 (no other port changes needed). Switches Android build to full dynamic backends (QVAC-18993): - GGML_CPU_STATIC=ON --> GGML_CPU_ALL_VARIANTS=ON - All backends (per-arch CPU + Vulkan + OpenCL) ship as MODULE .so loaded at runtime via ggml's GGML_BACKEND_DL loader. - Picks up the .so files into vcpkg's bin/ via post-install file(GLOB). Adds an `-isystem` shim that injects spirv-headers on the include path when the vulkan feature is on: the QVAC-18992 ggml-org v0.10.2 merge introduces ggml-vulkan.cpp code that uses spv::* enums unconditionally for SPIR-V capability injection (rounding-mode RTE). Vulkan-Headers itself no longer bundles spirv.hpp, so the standalone SPIRV-Headers tree must be on the include path. ggml-vulkan's CMakeLists doesn't find_package(SpirvHeaders) so we inject via CMAKE_CXX_FLAGS. version-date 2026-04-09 --> 2026-05-19 port-version 2 --> 3 (continues after tetherto#156's bump to 2026-04-09#2) Co-authored-by: Cursor <cursoragent@cursor.com>

cl.exe does not understand the GCC/Clang `-isystem` flag --- it treats it as a positional argument (a source file path), then tries to open the following include directory path as a source file and dies with: c1xx: fatal error C1083: Cannot open source file: 'C:/.../x64-windows/include': No such file or directory Surfaced on tetherto/qvac/pull/2124 prebuild / win32-x64 against whisper-cpp[vulkan]. The include shim now emits `/I<path>` on MSVC (and the legacy `/I` form, no space, for maximal cl-flavour compatibility) and keeps `-isystem <path>` on GCC/Clang. Note: this PR previously also carried the ggml-speech port bump (b4cf7b2) and the matching ggml-speech-side MSVC shim. Both have been dropped because the consumer-side migration to ggml-speech (QVAC-18992) is staying behind PR tetherto#13 / PR tetherto#28 for now; only the whisper-cpp bits are required to land for the Android dynamic-backend work on PR #2124. Co-authored-by: Cursor <cursoragent@cursor.com>

@GustavoA1604

… MSVC fix (QVAC-18300, QVAC-18993) (#152) * whisper-cpp: bump to 1.8.4.3 with Android OpenCL + dynamic-backend + spirv-headers (QVAC-18300, QVAC-18992, QVAC-18993) Brings the whisper-cpp port up to the upstream-sync snapshot at v1.8.4.3 (QVAC-18991, merged into tetherto/qvac-ext-lib-whisper.cpp master via PR #25) plus the Android speech-stack flags landed for QVAC-18300 + QVAC-18992 + QVAC-18993: - opencl feature (QVAC-18300): Android-only enable-path, OpenCL/Vulkan side-by-side, COOPMAT[2] disabled to keep Adreno-class GPUs healthy. - Android dynamic-backend mode (QVAC-18993): GGML_BACKEND_DL=ON, GGML_CPU_ALL_VARIANTS=ON, GGML_CPU_REPACK=ON. Static dispatcher + per-microarch CPU .so + GPU .so files side by side, picked by ggml's HWCAP-aware loader at runtime. - spirv-headers dependency for the vulkan feature (QVAC-18992): the upstream ggml-org v0.10.2 sync pulled in ggml-vulkan.cpp code that uses spv::* enums unconditionally for SPIR-V capability injection (RTE rounding-mode); Vulkan-Headers no longer bundles spirv.hpp, so the standalone SPIRV-Headers tree must be on the include path. Inject via CMAKE_CXX_FLAGS=-isystem since ggml-vulkan's CMakeLists doesn't find_package(SpirvHeaders). REF currently pins Zbig9000/qvac-ext-lib-whisper.cpp @ 14620c88 which is the tree-equivalent of merged PR #25 (upstream sync) + merged PR #27 (tts-cpp <atomic>) + still-open PR #28 (bundled-ggml Android dynamic-backend fixes). After PR #28 lands on tetherto/master and a v1.8.4.x tag is published, flip REPO -> tetherto and the tag/SHA (no other port changes needed). The previous port-version 2's two patch files (0001-ggml-allow-backend-dl-with-static-core.patch, 0002-ggml-android-cpu-variant-dlopen-fallback.patch) are now upstream-equivalent commits on whisper.cpp PR #28 --- ports is patch-free. SHA512 = 733effd6... matches the github.com/Zbig9000/qvac-ext-lib-whisper.cpp/archive/14620c88....tar.gz tarball verified via independent download + sha512sum. version 1.8.4.2 --> 1.8.4.3 port-version 1 --> 3 (continues after the previous port-version 2 patch-based recipe) Co-authored-by: Cursor <cursoragent@cursor.com> * whisper-cpp: fix spirv-headers -isystem shim on MSVC (QVAC-18993) cl.exe does not understand the GCC/Clang `-isystem` flag --- it treats it as a positional argument (a source file path), then tries to open the following include directory path as a source file and dies with: c1xx: fatal error C1083: Cannot open source file: 'C:/.../x64-windows/include': No such file or directory Surfaced on tetherto/qvac/pull/2124 prebuild / win32-x64 against whisper-cpp[vulkan]. The include shim now emits `/I<path>` on MSVC (and the legacy `/I` form, no space, for maximal cl-flavour compatibility) and keeps `-isystem <path>` on GCC/Clang. Note: this PR previously also carried the ggml-speech port bump (b4cf7b2) and the matching ggml-speech-side MSVC shim. Both have been dropped because the consumer-side migration to ggml-speech (QVAC-18992) is staying behind PR #13 / PR #28 for now; only the whisper-cpp bits are required to land for the Android dynamic-backend work on PR #2124. Co-authored-by: Cursor <cursoragent@cursor.com> * whisper-cpp: bump to 1.8.4.3#5 — repoint to tetherto/master after PR #28 merge (QVAC-18993, QVAC-19071) `tetherto/qvac-ext-lib-whisper.cpp` PR #28 merged today (2026-05-21, merge commit `f3102199`), completing the Group-1/2 merge chain on `tetherto/master`: - PR #25 (QVAC-18991) merged 2026-05-20 — upstream whisper.cpp sync - PR #27 (QVAC-18966) merged 2026-05-20 — tts-cpp chatterbox <atomic> fix - PR #28 (QVAC-18993) merged 2026-05-21 — ggml-backend Android dynamic backend + per-arch CPU dlopen fallback So `tetherto/master` now carries every commit this port previously pinned from `Zbig9000/qvac-ext-lib-whisper.cpp@14620c8857fc2893`. Repoints the `vcpkg_from_github` call: REPO Zbig9000/qvac-ext-lib-whisper.cpp -> tetherto/qvac-ext-lib-whisper.cpp REF 14620c8857fc289313a3b0a82c9ce69a -> f3102199642e78bb2beee6b9e9537604 SHA512 733effd6f77de859bd9f1cf1b6dfe492… -> 64b102677abae7825985c946b1103cda… HEAD_REF QVAC-18993-bundled-ggml-android-… -> master `diff -rq` of the two source tarballs is empty outside `parakeet-cpp/` and `tts-cpp/` (separate vcpkg ports — not consumed by this port). The whisper-cpp source itself is byte-identical between `14620c88` and `f3102199`, so this is a REF-only port-version bump: same recipe, same features, same patches list (still empty), same build output. Also drops the "TEMPORARY pinning to Zbig9000 fork" block from the top of `portfile.cmake` --- no longer applicable now that the upstream PR chain has landed. Closes the registry-side half of [QVAC-19071](https://tetherapp.atlassian.net/browse/QVAC-19071) ("Update qvac-registry-vcpkg and addon with new port versions") for this release cycle. Consumer-side half (re-pinning `packages/transcription-whispercpp/vcpkg-configuration.json`) goes into qvac PR #2124 in a follow-up commit. [QVAC-18993][QVAC-19071] Co-authored-by: Cursor <cursoragent@cursor.com> * whisper-cpp: address Gustavo PR #152 review (1.8.4.3#0, drop history, drop comment block) Review comments from @GustavoA1604 on PR #152 (#152): 1. `ports/whisper-cpp/portfile.cmake`: "Dont add these comments" -> dropped the 19-line header that explained the REF history / tetherto vs Zbig9000 fork relation / future-bump notes. 2. `ports/whisper-cpp/vcpkg.json`: "Port version should start from 0, not 5" -> reset `port-version` 5 -> 0. 3. `versions/w-/whisper-cpp.json`: "Add only one entry here, version '1.8.4.3', port-version 0" -> collapsed the three historical `1.8.4.3` entries (port-versions 3, 4, 5 -- intermediate states that were never consumed off-fork) into a single entry at port-version 0 with the new git-tree `b4962d7acd7ce05fce118792a167e7aee36f1eba`. Older versions (1.8.4.2, 1.8.4.1, 1.7.x) untouched. Also synced `versions/baseline.json` whisper-cpp port-version to 0. REPO + REF + SHA512 (tetherto/qvac-ext-lib-whisper.cpp@f3102199, the PR #28 merge commit) unchanged from the previous HEAD `f287037`. [QVAC-18993][QVAC-19071] Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>

Picks up tetherto/qvac-ext-ggml@speech HEAD c9126afc (merge commit of qvac-ext-ggml PR tetherto#13: "QVAC-18992: merge ggml-org @ 19eac6f0 (v0.10.2) into speech"). The merge brings in: c9126afc Merge pull request tetherto#13 from Zbig9000/QVAC-18992-merge-ggml-from-whisper-cpp e31785e4 fix(metal): restore lost 'typedef struct {' before ggml_metal_kargs_supertonic_depthwise_1d (caught by qvac CI Apple prebuild matrix via an overlay on tetherto/qvac#2270) d39c0d29 metal: stride-aware src indexing in kernel_pad_f32 / kernel_pad_reflect_1d_f32 (fixes Mac M2 PAD test failure) 166c4e12 Merge ggml-org @ 19eac6f0 into speech (sync to v0.10.2) PR tetherto#13 also brings in PR tetherto#11 (GustavoA1604 Android per-arch CPU dlopen fallback), which was already wired through port-version 4 via the GGML_CPU_ALL_VARIANTS=ON + GGML_CPU_REPACK=ON shape introduced in port-version 3 -- no port-side change needed for that. Build changes vs port-version 4: * Add patches/0001-ggml-vulkan-find-spirv-headers.patch wiring SPIRV-Headers into ggml-vulkan. The v0.10.2 sync added an unconditional #include <spirv/unified1/spirv.hpp> in src/ggml-vulkan/ggml-vulkan.cpp, but the upstream ggml-vulkan CMakeLists.txt never finds spirv-headers nor wires its include dir into the ggml-vulkan target. Patch finds the package and links it when available, gated on the "vulkan" feature. * Add spirv-headers as a dependency of the "vulkan" feature so the patched find_package(SPIRV-Headers QUIET) actually resolves to a vcpkg-installed package. Validated end-to-end through tetherto/qvac#2270's full CI matrix: - 9/9 prebuild triplets (linux-x64/arm64, win32-x64, darwin-arm64/x64, android-arm64, ios-arm64 + 2 simulators) - 107/107 C++ addon tests on linux-x64 - 5/5 platform integration test suites - iOS + Android E2E on AWS Device Farm Co-authored-by: Cursor <cursoragent@cursor.com>

…pp re-validation (QVAC-19236, QVAC-18992, QVAC-19071) (#169) * whisper-cpp 1.8.5: migrate to ggml-speech + expose metal feature Two ticket deliverables combined into one consistent port rewrite: QVAC-18992 — Migrate to use ggml speech branch ---------------------------------------------- whisper-cpp now consumes the system-installed ggml provided by the `ggml-speech` port (same shape as parakeet-cpp and tts-cpp), instead of building the bundled `qvac-ext-lib-whisper.cpp/ggml/` subdirectory. Driven by -DWHISPER_USE_SYSTEM_GGML=ON; whisper.cpp's top-level CMake then calls `find_package(ggml CONFIG REQUIRED)` and aliases the `ggml::ggml` target to its internal `ggml` target. The bundled ggml source tree still exists in the upstream tarball but is no longer walked at configure time. All backend wiring is delegated to ggml-speech: - GGML_METAL / GGML_VULKAN / GGML_OPENCL / GGML_CUDA - GGML_BACKEND_DL=ON on Android (dynamic-backend mode) - GGML_CPU_ALL_VARIANTS=ON / GGML_CPU_REPACK=ON on Android (per-arch CPU MODULE .so files) - GGML_VULKAN_DISABLE_COOPMAT[2]=ON on Android (Adreno NDK) - spirv-headers `-isystem` shim for Vulkan - Android NDK Vulkan-Headers download - libqvac-speech-ggml-* output filename prefix Side effects: - The Vulkan-Headers download block is gone from this portfile; ggml-speech handles it. android-vulkan-version.cmake deleted. - The MSVC `/I` vs GCC/Clang `-isystem` spirv-headers shim is gone from this portfile; ggml-speech handles it. - The DL_BACKENDS install-tree fiddling is gone; the libqvac-speech-ggml-*.so files are installed by ggml-speech into ${VCPKG_INSTALLED_DIR}/<triplet>/lib/, which the transcription-whispercpp addon already picks up via get_target_property(... LOCATION) on the ggml::<backend> imported targets. - whisper-cpp + parakeet-cpp + tts-cpp now share the same backend binary set on every triplet (was: whisper-cpp brought a separate libqvac-ggml-* set, parakeet/tts brought libqvac-speech-ggml-*). Single source of truth. QVAC-19236 — Expose backend selection as features ------------------------------------------------- Add the `metal` feature (was unconditionally ON for macOS / OFF for iOS in the portfile) so all 3 GPU backends are now declarative: whisper-cpp[metal] -> ggml-speech[metal] (osx | ios) whisper-cpp[vulkan] -> ggml-speech[vulkan] (linux | windows | android) whisper-cpp[opencl] -> ggml-speech[opencl] (android) Each whisper-cpp feature simply propagates into the matching ggml-speech feature (with the platform guard kept). Consumers can express the full GPU matrix declaratively in their own vcpkg.json (the transcription-whispercpp addon does exactly this in a companion PR — selecting [metal] for osx only, since iOS Metal still has a separate XPC/MTLCompiler runtime crash being investigated; the iOS binary stays on the CPU backend by simply not selecting [metal]). Whisper-cpp REF --------------- Bumped to v1.8.5 = 738d2e9e (tetherto/qvac-ext-lib-whisper.cpp@master), which is the merge of #33 ("update to v1.8.5 and sync vendored whisper.cpp + ggml to ggml-org upstream"). Pure upstream sync — no tetherto-specific behavior change at the consumer level beyond the ggml-source switch above. Result ------ portfile.cmake: 150 -> ~55 lines (much closer to parakeet-cpp / tts-cpp shape). Total diff: -174 / +56. Version bump: 1.8.4.3#1 -> 1.8.5#0 (treating the version-string change + the ggml-source switch as a fresh baseline rather than a port-revision bump). Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Cursor <cursoragent@cursor.com> * ggml-speech: bump to 2026-05-27#0 (PR #13 merged on speech) Picks up tetherto/qvac-ext-ggml@speech HEAD c9126afc (merge commit of qvac-ext-ggml PR #13: "QVAC-18992: merge ggml-org @ 19eac6f0 (v0.10.2) into speech"). The merge brings in: c9126afc Merge pull request #13 from Zbig9000/QVAC-18992-merge-ggml-from-whisper-cpp e31785e4 fix(metal): restore lost 'typedef struct {' before ggml_metal_kargs_supertonic_depthwise_1d (caught by qvac CI Apple prebuild matrix via an overlay on tetherto/qvac#2270) d39c0d29 metal: stride-aware src indexing in kernel_pad_f32 / kernel_pad_reflect_1d_f32 (fixes Mac M2 PAD test failure) 166c4e12 Merge ggml-org @ 19eac6f0 into speech (sync to v0.10.2) PR #13 also brings in PR #11 (GustavoA1604 Android per-arch CPU dlopen fallback), which was already wired through port-version 4 via the GGML_CPU_ALL_VARIANTS=ON + GGML_CPU_REPACK=ON shape introduced in port-version 3 -- no port-side change needed for that. Build changes vs port-version 4: * Add patches/0001-ggml-vulkan-find-spirv-headers.patch wiring SPIRV-Headers into ggml-vulkan. The v0.10.2 sync added an unconditional #include <spirv/unified1/spirv.hpp> in src/ggml-vulkan/ggml-vulkan.cpp, but the upstream ggml-vulkan CMakeLists.txt never finds spirv-headers nor wires its include dir into the ggml-vulkan target. Patch finds the package and links it when available, gated on the "vulkan" feature. * Add spirv-headers as a dependency of the "vulkan" feature so the patched find_package(SPIRV-Headers QUIET) actually resolves to a vcpkg-installed package. Validated end-to-end through tetherto/qvac#2270's full CI matrix: - 9/9 prebuild triplets (linux-x64/arm64, win32-x64, darwin-arm64/x64, android-arm64, ios-arm64 + 2 simulators) - 107/107 C++ addon tests on linux-x64 - 5/5 platform integration test suites - iOS + Android E2E on AWS Device Farm Co-authored-by: Cursor <cursoragent@cursor.com> * tts-cpp + parakeet-cpp: bump port-version against ggml-speech 2026-05-27 ggml-speech bumped to 2026-05-27#0 in this PR will auto-apply via baseline to every consumer port that has version>= on it. tts-cpp and parakeet-cpp must declare they have been validated against the new ggml-speech to keep the registry self-consistent. tts-cpp: 2026-05-20 -> 2026-05-20#1 - version>=ggml-speech bumped to 2026-05-27 (was 2026-04-09#4) parakeet-cpp: 2026-05-20#2 -> 2026-05-20#3 - version>=ggml-speech bumped to 2026-05-27 (was 2026-04-09#3) Local validation (x64-linux, vulkan feature) against this registry tree: - tts-ggml addon: vcpkg resolves clean, build links clean, 35 C++ unit tests pass, 61 JS unit tests pass - transcription-parakeet addon: vcpkg resolves clean, build links clean, 32 C++ unit tests pass, 17 JS unit tests pass Co-authored-by: Cursor <cursoragent@cursor.com> * whisper-cpp: bump version>=ggml-speech to 2026-05-27 The version>= constraint on ggml-speech was still 2026-04-09#4 (carried over from before the system-ggml migration). whisper-cpp@1.8.5 only works against the new ggml-speech@2026-05-27 (v0.10.2 vendored sources, new symbol set, spirv-headers Vulkan wiring), so the constraint must reflect that minimum. In practice the resolver always picked 2026-05-27 because that is the baseline value, so this is metadata-only and not a behavior change for either the addon CI run or the local file:// validation. It is the correct declaration so a future consumer with a stale baseline cannot combine whisper-cpp@1.8.5 with the old ggml-speech. Co-authored-by: Cursor <cursoragent@cursor.com> * ggml-speech: pin spirv-headers vulkan dep to version>=1.4.341.0 Without a version>= constraint, the resolved spirv-headers version depends entirely on the consumer's microsoft/vcpkg baseline. Pin to 1.4.341.0 to match the convention already used by qvac-fabric (the other speech-stack port that depends on spirv-headers via vulkan), keep both ports resolvable from the same SPIRV-Headers version when they coexist in a consumer manifest, and ensure consumers with an older baseline still pick up a known-good SPIRV-Headers. Local validation on x64-linux: vcpkg upgrades spirv-headers from the addon's baseline 1.4.304.1 to the required 1.4.341.0 cleanly, the ggml-vulkan patch builds against the new headers, the full transcription-whispercpp addon builds + 107/107 cpp tests + 30/30 unit tests pass. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>

Updated port qvac-lib-inference-addon-cpp to v0.6.1

029373d

olyasir approved these changes Jul 9, 2025

View reviewed changes

hamlingreen approved these changes Jul 9, 2025

View reviewed changes

hamlingreen merged commit 98300ba into tetherto:main Jul 9, 2025

Zbig9000 mentioned this pull request May 20, 2026

whisper-cpp: bump to 1.8.4.3 with Android OpenCL + dynamic backends + MSVC fix (QVAC-18300, QVAC-18993) #152

Merged

Zbig9000 mentioned this pull request May 27, 2026

feat: whisper-cpp 1.8.5 + ggml-speech 2026-05-27 + tts-cpp/parakeet-cpp re-validation (QVAC-19236, QVAC-18992, QVAC-19071) #169

Merged

4 tasks

Zbig9000 mentioned this pull request Jun 2, 2026

ggml-speech: bump to speech HEAD with Adreno OpenCL selection (QVAC-18993) #178

Merged

2 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

QVAC-3127: Updated port qvac-lib-inference-addon-cpp to v0.6.1#13

QVAC-3127: Updated port qvac-lib-inference-addon-cpp to v0.6.1#13
hamlingreen merged 1 commit into
tetherto:mainfrom
jpgaribotti:QVAC-3127

jpgaribotti commented Jul 9, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

jpgaribotti commented Jul 9, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants