[SDKv2] Migrate WinML EP downloads to WinML 2.x (reg-free runtime)#788
Open
bmehta001 wants to merge 9 commits into
Open
[SDKv2] Migrate WinML EP downloads to WinML 2.x (reg-free runtime)#788bmehta001 wants to merge 9 commits into
bmehta001 wants to merge 9 commits into
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
bmehta001
changed the title
bmehta001
force-pushed
the
bhamehta/flcore/winml-2-ep-downloads
branch
from
44fb8d1 to
ae5ad90
Compare
Switch from `Microsoft.WindowsAppSDK.ML` 1.8.2192 (WinML 1.x, WinAppSDK
bootstrap required, Win11 24H2+) to `Microsoft.Windows.AI.MachineLearning`
2.1.6 (WinML 2.x, registration-free, Win10 19H1+). This brings Foundry-Local
in line with the same migration neutron-server completed.
Highlights:
* Remove WinAppSDK Bootstrap plumbing across all SDKs. The `Bootstrap`
`additionalSettings` key — which used to flip on WinAppSDK init in the
native layer — is gone in every binding (C++, C#, JS, Python). It was an
internal init knob; no public surface signaled it as a stable contract.
- C++: delete winml_bootstrap.{h,cc}, the WinAppSdkBootstrap link target,
the Bootstrap.dll post-build copy, and the additional_options key
handling in Manager::Create / Destroy.
- C#: drop the `IS_WINML` default that injected Bootstrap=true.
Lower TFM from net9.0-windows10.0.26100.0 to net9.0-windows10.0.18362.0.
- JS: delete applyBootstrapAutoDetect and its test; drop Bootstrap.dll
from copy-native script.
- Python: drop `Bootstrap=false` examples from README and integration
test.
* Unify ORT to 1.25.1 / OnnxRuntimeGenAI to 0.13.2 for both the WinML and
non-WinML flavors. Delete sdk_v2/deps_versions_winml.json and the
`FOUNDRY_LOCAL_USE_WINML` branch in FindOnnxRuntime.cmake /
FindOnnxRuntimeGenAI.cmake / the python build backend.
* Collapse cuda_ep_bootstrapper.cc to the single ORT-1.25.1 URL / binary
set (previously branched on WinML for the older 1.23.2 build).
* Drop the WebGPU-EP skip on WinML builds (both flavors now satisfy ORT
API >= 24).
* Drop the IsWindows11_24H2OrLater() runtime guard in
winml_ep_bootstrapper.cc; LoadLibraryW is a sufficient probe.
* Gate `find_package(WinMLEpCatalog)` behind `FOUNDRY_LOCAL_USE_WINML`
so non-WinML builds don't silently link the catalog DLL.
* CMake/cmake-modules: update DLL path
`runtimes-framework/<rid>/native/` -> `runtimes/<rid>/native/` and
bump default `WINML_EP_CATALOG_VERSION` to 2.1.6.
* Pipelines: bump `cppWinmlVersion` to 2.1.6, drop `cppOrtVersionWinml`
and the entire `Microsoft.WindowsAppSDK.Foundation` resolution +
Bootstrap.dll staging in steps-prefetch-nuget.yml /
steps-build-windows.yml.
* Nuget pack: replace `Microsoft.WindowsAppRuntime.Bootstrap.dll` with
`Microsoft.Windows.AI.MachineLearning.dll` in OPTIONAL_SIBLINGS.
* Bump gtest `DISCOVERY_TIMEOUT` to 60 for foundry_local_tests and
cache_only_tests; WinML's delay-loaded DLL resolution + static
initializers can exceed the 5 s default during test discovery.
Verified:
* `python sdk_v2/cpp/build.py --config RelWithDebInfo --skip_examples`
(non-WinML) builds clean; 820 unit/cache tests pass.
* `python sdk_v2/cpp/build.py --config RelWithDebInfo --skip_examples
--use_winml` builds clean; FindWinMLEpCatalog.cmake downloads
Microsoft.Windows.AI.MachineLearning 2.1.6 from nuget.org;
Microsoft.Windows.AI.MachineLearning.dll is co-located with
foundry_local.dll in the build output.
* Targeted ctest run on the WinML build:
`ctest -R "EpDetector|WinML|ManagerWebServiceTest|CacheOnlyTest"` ->
18/18 pass.
Out of scope (deferred): WebGPU manifest-based granular updates;
adopting WinML's bundled onnxruntime.dll.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
bmehta001
force-pushed
the
bhamehta/flcore/winml-2-ep-downloads
branch
from
ae5ad90 to
c240a00
Compare
The helper is only referenced from DiscoverProviders' EP-catalog code path. When FOUNDRY_LOCAL_HAS_EP_CATALOG=0 (non-WinML Windows build) the file is still compiled but the helper has no callers, which can trip MSVC C4505 (unreferenced local function has been removed) under /W4 builds. Moving the function definition inside the same preprocessor guard that gates its sole call site makes the compilation symmetric. No behavior change. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The find-module advertised WINML_EP_CATALOG_HEADER_DIR as a public output (set as CACHE PATH ... FORCE and printed via message(STATUS)), but no caller in the repo reads it. Headers reach consumers through the WindowsML::Api target's INTERFACE_INCLUDE_DIRECTORIES, propagated by the WinMLEpCatalog::WinMLEpCatalog alias. The companion WINML_EP_CATALOG_DLL_DIR is genuinely consumed by the post-build DLL-copy step in sdk_v2/cpp/CMakeLists.txt, so only the header variable is dead. Drop the cache var, its STATUS line, and the corresponding header-block doc entry. Verified zero remaining references via 'git grep' and a clean configure + build of foundry_local on Windows. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR migrates the WinML EP download/discovery path from WinML 1.x (Windows App SDK bootstrap required) to WinML 2.x (Microsoft.Windows.AI.MachineLearning, reg-free runtime), and unifies ORT/GenAI pins across WinML and non-WinML flavors to simplify build + packaging across C++, C#, JS, Python, and CI.
Changes:
- Removes Windows App SDK bootstrap plumbing (
BootstrapadditionalSettings, bootstrap DLL staging, and native bootstrap helper) across all SDK bindings. - Switches WinML EP catalog acquisition to
Microsoft.Windows.AI.MachineLearning(NuGet + first-party CMake config) and updates packaging/staging to ship the reg-free runtime DLL where needed. - Unifies ORT/GenAI version pins (deletes WinML-specific deps JSON and removes WinML branching in CMake and the Python v2 build backend).
Reviewed changes
Copilot reviewed 32 out of 32 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| sdk_v2/python/test/integration/test_configuration_native.py | Updates integration test to stop using the removed Bootstrap additional setting. |
| sdk_v2/python/README.md | Removes WinML-only Bootstrap=false example from docs. |
| sdk_v2/python/pyproject.toml | Updates comments to reflect single deps JSON source for both wheel flavors. |
| sdk_v2/python/_build_backend/init.py | Drops WinML-specific deps JSON selection; always rewrites from deps_versions.json. |
| sdk_v2/js/test/bootstrap-autodetect.test.ts | Deletes tests for bootstrap auto-detect (no longer relevant with WinML 2.x reg-free runtime). |
| sdk_v2/js/src/foundryLocalManager.ts | Removes bootstrap auto-detect logic from manager initialization. |
| sdk_v2/js/script/copy-native.mjs | Stops copying Bootstrap.dll; now copies Microsoft.Windows.AI.MachineLearning.dll. |
| sdk_v2/deps_versions_winml.json | Removes WinML-specific ORT pin file (pins are unified). |
| sdk_v2/cs/src/Microsoft.AI.Foundry.Local.csproj | Lowers WinML package TFM to Windows 10 19H1-era baseline. |
| sdk_v2/cs/src/FoundryLocalManager.cs | Removes WinML bootstrap default injection into AdditionalSettings. |
| sdk_v2/cpp/test/sdk_api/ep_detection_test.cc | Updates WinML EP test comment to reflect Win10 19H1+ support. |
| sdk_v2/cpp/test/CMakeLists.txt | Increases gtest discovery timeout to accommodate WinML build startup costs. |
| sdk_v2/cpp/src/winml_bootstrap.h | Deletes WinAppSDK bootstrap helper header. |
| sdk_v2/cpp/src/winml_bootstrap.cc | Deletes WinAppSDK bootstrap helper implementation. |
| sdk_v2/cpp/src/manager.cc | Removes bootstrap lifecycle; enables WebGPU EP path for WinML builds now that ORT is unified. |
| sdk_v2/cpp/src/ep_detection/winml_ep_bootstrapper.cc | Removes OS-version gating; improves diagnostics when the WinML runtime DLL is absent. |
| sdk_v2/cpp/src/ep_detection/cuda_ep_bootstrapper.cc | Collapses CUDA EP download to a single ORT-aligned payload (no WinML branching). |
| sdk_v2/cpp/nuget/pack.py | Packages Microsoft.Windows.AI.MachineLearning.dll as the optional WinML sibling DLL. |
| sdk_v2/cpp/docs/MigrationPlan_20260410.md | Updates migration plan documentation for WinML 2.x acquisition and behavior. |
| sdk_v2/cpp/docs/EpDetectionPlan.md | Updates EP detection plan to WinML 2.x reg-free runtime and new package layout. |
| sdk_v2/cpp/docs/CppPortGuide.md | Updates port guide WinML requirements note to Win10 19H1+ reg-free runtime. |
| sdk_v2/cpp/CMakeLists.txt | Gates find_package(WinMLEpCatalog) behind FOUNDRY_LOCAL_USE_WINML; removes bootstrap linking/copy; ensures WinML DLL copy uses catalog DLL dir. |
| sdk_v2/cpp/cmake/FindWinMLEpCatalog.cmake | Switches acquisition to Microsoft.Windows.AI.MachineLearning and uses the package’s first-party CMake config to define targets and DLL dir. |
| sdk_v2/cpp/cmake/FindOnnxRuntimeGenAI.cmake | Removes WinML-vs-standard package branching; uses a single GenAI package. |
| sdk_v2/cpp/cmake/FindOnnxRuntime.cmake | Removes WinML-specific deps file selection; uses unified ORT pin. |
| sdk_v2/cpp/build.py | Updates --use_winml messaging and changes override define to WINML_EP_CATALOG_VERSION. |
| .pipelines/v2/templates/steps-prefetch-nuget.yml | Updates WinML prefetch to download the reg-free package directly (no transitive Foundation resolution). |
| .pipelines/v2/templates/steps-build-windows.yml | Updates native staging to include Microsoft.Windows.AI.MachineLearning.dll for WinML builds. |
| .pipelines/v2/templates/stages-sdk-v2.yml | Removes WinML-specific ORT version parameter wiring. |
| .pipelines/v2/templates/stages-build-native.yml | Unifies WinML and non-WinML builds on the same ORT version parameter. |
| .pipelines/v2/sdk_v2-pipeline-plan.md | Updates pipeline plan documentation for unified ORT pins and WinML 2.x package handling. |
| .pipelines/foundry-local-packaging.yml | Updates packaging pipeline variables to use WinML 2.x version and removes WinML-specific ORT version variable. |
The RTL_OSVERSIONINFOW name (and PRTL_OSVERSIONINFOW pointer alias) live in <winnt.h>, transitively included via <windows.h> — so the previous code did compile cleanly. But the canonical Win32 type is OSVERSIONINFOW, which is the same struct (both names appear in the same typedef in <winnt.h>) and is what all the documented Win32 RTL_OSVERSIONINFOW consumers use. Switching to the public name removes any ambiguity for readers/static analysers that wonder whether <winternl.h> is required (it isn't, but the Rtl- prefix invites the question). Pure rename — no behavior change. foundry_local builds clean on Windows. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The existing EP detection suite only exercised catalog enumeration (WinMLEpCatalogCreate + WinMLEpCatalogEnumProviders) and the legacy Foundry-managed CUDA/WebGPU download path. The WinML 2.x EnsureReady -> GetLibraryPath -> ORT register chain had no automated coverage despite being the headline feature of this PR. Add DownloadAndRegister_WinMLEp_RegistersFromOsCatalog: picks any discoverable EP that SharedTestEnv has not already registered (i.e. one served by the OS WinML catalog, not Foundry's own download), invokes DownloadAndRegisterEps for just that name, and asserts the post-state surfaces through GetDiscoverableEps with is_registered=true. Skipped via GTEST_SKIP on minimal CI images that expose no WinML EPs, so it never hard-fails Linux/macOS or stripped Windows runners. Verified locally on Win11 with Intel OpenVINO EP installed: [info] EP registration: 'OpenVINOExecutionProvider' registered successfully (library=C:\\\\Program Files\\\\WindowsApps\\\\Microsoft CorporationII.WinML.Intel.OpenVINO.EP.1.8_*\\\\onnxruntime_ providers_openvino_plugin.dll, version=1.4.1+f33af4f) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
GetRepoRoot in Utils.cs walks parents looking for a '.git' directory to anchor test data lookups. In a git worktree '.git' is a regular file containing 'gitdir: <main repo>/.git/worktrees/<name>' rather than a directory, so Directory.Exists returns false and the walk runs to the drive root, throwing 'Could not find git repository root from test file location' before any test executes. Accept either form so dotnet test works from worktrees as well as regular checkouts. No other resolution logic changes. Surfaced while running build_and_test_all.ps1 -UseWinml from a worktree; pre-existing bug (Utils.cs last touched in 93e400a, unrelated to this PR). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Previously winml_ep_bootstrapper.cc was added to FOUNDRY_LOCAL_PLATFORM_SOURCES
unconditionally for any Windows build, and its body used #if FOUNDRY_LOCAL_HAS_EP_CATALOG
to stub out the implementation when the WinML EP catalog NuGet package was
not available. That meant the file was still parsed/compiled (and added to the
objects archive) on stock Windows builds with USE_WINML=OFF, even though every
exported function was a no-op.
Two clean-ups:
1. CMake now adds the source only when WinMLEpCatalog_FOUND is true. With the
default FOUNDRY_LOCAL_USE_WINML=OFF (no find_package call), this excludes
the translation unit entirely. Verified with both configs:
- USE_WINML=ON -> winml_ep_bootstrapper.obj present, full path runs
- USE_WINML=OFF -> no winml_ep_bootstrapper.obj, foundry_local.dll links
and all test exes build
2. manager.cc now guards both the #include and the DiscoverProviders() call
site on FOUNDRY_LOCAL_HAS_EP_CATALOG instead of just _WIN32. Non-WinML
Windows builds skip the call cleanly; the Windows block above still owns
<windows.h> / <filesystem> for the other Windows-only includes.
Because the .cc is no longer compiled when HAS_EP_CATALOG=0, the internal
#if !FOUNDRY_LOCAL_HAS_EP_CATALOG stub branches in DownloadAndRegister() and
DiscoverProviders() (and the matching guards in the header) are now dead
code and have been removed. The remaining file is structurally guaranteed
to see HAS_EP_CATALOG=1.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The previous docstring ("Windows 11 24H2+ (build 26100) only") was
overly restrictive. The bundled Microsoft.Windows.AI.MachineLearning
redist DLL loads on Windows 10 19H1+ (build 18362) — that's the floor
for the code path itself. Build 26100 (Win11 24H2) is only the floor
for the OS to actually have any WinML EPs installed via Store/WU; on
earlier builds enumeration returns an empty list and the caller falls
back to other bootstrappers.
No behavior change — comment only.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Migrates WinML EP-download path from
Microsoft.WindowsAppSDK.ML1.8.2192 (WinML 1.x, requires the Windows App SDK bootstrap and Win11 24H2+) toMicrosoft.Windows.AI.MachineLearning2.1.70 (WinML 2.x, registration-free, Win10 19H1+)Highlights
IsWindows11_24H2OrLater()runtime guard inwinml_ep_bootstrapper.cc, sinceLoadLibraryWis a sufficient probe.find_package(WinMLEpCatalog)behindFOUNDRY_LOCAL_USE_WINMLso non-WinML builds don't silently link the catalog DLL.runtimes-framework/<rid>/native/→runtimes/<rid>/native/and bump defaultWINML_EP_CATALOG_VERSIONto 2.1.70.cppWinmlVersionto 2.1.70, dropcppOrtVersionWinmland the entireMicrosoft.WindowsAppSDK.Foundationresolution +Bootstrap.dllstaging insteps-prefetch-nuget.yml/steps-build-windows.yml.Microsoft.WindowsAppRuntime.Bootstrap.dllwithMicrosoft.Windows.AI.MachineLearning.dllinOPTIONAL_SIBLINGS.DISCOVERY_TIMEOUTto 60 s forfoundry_local_testsandcache_only_tests— the WinML build's delay-loaded DLL resolution + static initializers can exceed the 5 s default.WinML 2.x EP semantics (informational)
WinMLEpEnsureReadyAsync(WinMLAsyncBlock*), but the OS-side MSIX/BITS work is largely serialized anyway. Left as a future optimization.WinMLEpCatalogHandle) is only created during EnsureReady at the beginning. The 2.x C API has no Refresh/Invalidate, so if new EPs are released mid-process, they will only be visible after process restart.AzureModelCatalogcache is correctly invalidated inManager::DownloadAndRegisterEps(manager.cc:547) after a successful register, so model-filter results reflect the new EP set immediately.Maybe the extra error-checking in @sdk_v2/cpp/src/ep_detection/winml_ep_bootstrapper.cc is unnecessary, but I have added it for diagnostics.