Repository navigation
Add OSS CI for the Native CPU engine - #23937
Open
JakeStevens wants to merge 6 commits into
Open
JakeStevens wants to merge 6 commits into
JakeStevens wants to merge 6 commits into
Conversation
Summary: Add `ggml-org/llama.cpp` under `backends/native/third-party`, pinned to `620d2225cc436ab0b001e3200e590e3b286ef9ab`, matching the internal dependency. The full submodule retains the upstream license and copyright notices. Authored with AI assistance from Codex. Differential Revision: D125694754
…n` runner (pytorch#23811) Summary: Pull Request resolved: pytorch#23811 Add engine-independent CMake libraries for the native graph, PTN package reader, program runtime, engine interface, and standalone API. `EXECUTORCH_BUILD_NATIVE` enables the common libraries; `EXECUTORCH_BUILD_NATIVE_VULKAN` also enables `native_vulkan_engine`. `EXECUTORCH_BUILD_NATIVE_VISION_RUNNER` (requires `EXECUTORCH_BUILD_NATIVE_VULKAN`) additionally builds the `examples/vision` classification runner as `run_classification` plus its `native_runner_utils` library. The runner links `native_vulkan_engine` and gflags and installs to `bin/`. Its existing `test_runner_utils.cpp` coverage runs as `native_runner_utils_test` under `EXECUTORCH_BUILD_TESTS`. Authored with Codex and Muse Code. Differential Revision: D125084367
Summary: Add separate Linux jobs for `runtime`, `ggml`, and `vulkan`, running each native test suite once and building `run_classification` in the Vulkan job. Scope PR triggers to relevant build inputs. Authored with AI assistance from Codex. Differential Revision: D125695225
Summary: Add `CPUEngineHost` and `CPUEngineContext` using the existing CPU backend's provider selection, memory planning, and execution. Consume standard Native preprocessing output by materializing supported views and functionalizing supported in-place activations during engine compilation. The engine integrates with `Model`/`Session`, shares package constants across methods, preserves inputs across repeated execution, and converts host dtypes with checked integer narrowing. Support static, unquantized graphs with contiguous constants and public I/O; reject unsupported aliasing and mutation semantics. Add CMake libraries and installed targets for the CPU runtime, providers, and engine. `EXECUTORCH_BUILD_NATIVE_CPU` requires XNNPACK and optimized kernels. Include the CPU engine integration suite in CTest. Authored with OpenAI Codex. Differential Revision: D125540986
Summary: Move classification package loading, FP32 I/O, labels, and reference comparison into `ClassificationRunner`, following the HF LLM runner's engine factory pattern. Add `run_classification_cpu` and the explicit `run_classification_vulkan` target while retaining the existing Vulkan `run_classification` command. Share the runner implementation in Buck and CMake, with engine-specific entry points. `EXECUTORCH_BUILD_NATIVE_VISION_RUNNER` accepts CPU, Vulkan, or both; the CPU engine and its CMake libraries come from the preceding commit. Authored with OpenAI Codex. Differential Revision: D125540991
Summary: Add a CPU job to the Native Engines workflow that builds `run_classification_cpu` and runs `native_cpu_engine_test` with XNNPACK and optimized kernels enabled. Update dependency triggers, documentation, and xplat mirrors. Authored with OpenAI Codex. Differential Revision: D125722080
JakeStevens
requested review from
SS-JIA,
kirklandsign and
larryliu0820
as code owners
October 16, 2026 18:54
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23937
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New FailuresAs of commit b1cdc99 with merge base c45d76f ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D125722080. |
This PR needs a
|
This branch has not been deployed
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
1 participant
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:
Add a CPU job to the Native Engines workflow that builds
run_classification_cpuand runsnative_cpu_engine_testwith XNNPACK and optimized kernels enabled. Update dependency triggers, documentation, and xplat mirrors.Authored with OpenAI Codex.
Differential Revision: D125722080