feat(hipep): add hipep-backend selected via profile=llm#23
Open
zz002 wants to merge 5 commits into
Open
Conversation
Add the hipep backend to the AMD GPU umbrella EP: load the pre-built hipep-backend plugin EP DLL as a third backend (alongside DirectML and MIGraphX) and route to it when the user selects profile=llm. - Profile::Llm parses "llm" / "3"; gpu_ep.cc routes profile=llm to ProviderFactory::CreateHipepBackend. - ProviderFactory loads hipep-backend and forwards CreateEp / ReleaseEp to it, mirroring the DirectML/MIGraphX backend pattern. hipep is a pre-built plugin EP DLL loaded at runtime, so no ROCm SDK is required to build amdgpu-ep. - CreateEp forwards the ORT-selected hardware device(s) + ep_metadata to the backend's CreateEp. Unlike DirectML/MIGraphX, hipep's CreateEp rejects num_devices == 0, so the umbrella must pass the selected device. DirectML and MIGraphX paths are unchanged. Co-authored-by: Cursor <cursoragent@cursor.com>
…ctML/MIGraphX The hipep backend no longer requires the umbrella to forward the ORT-selected device: its CreateEp now tolerates a null device array / num_devices == 0 (ROCm/MorphiZen#234). Drop the devices/ep_metadata parameters from ProviderFactory::CreateHipepBackend and the ExecutionProvider constructor and pass nullptr/nullptr/0, so the hipep path matches the DirectML and MIGraphX backends and the EP constructor keeps the same signature as the sibling EPs. Co-authored-by: Cursor <cursoragent@cursor.com>
Add src/hipep parallel to directml/migraphx. It builds hipep-backend.dll, a thin pass-through OrtEpFactory that loads hipep.dll, forwards CreateEpFactories, and returns the HIP EP's factory unchanged so the AMD GPU umbrella forwards to it directly. ReleaseEpFactory forwards to the HIP EP and unloads the DLL. Only a single factory is supported. Wired via a new USE_HIPEP option (forced on by USE_AMDGPU) and add_subdirectory(hipep). Co-authored-by: Cursor <cursoragent@cursor.com>
|
|
CreateEpFactories can be invoked more than once (e.g. a real session plus the device-init session in OGA). The previous single-handle logic reloaded the DLL on each call (leaking the earlier handle) and unloaded it on the first ReleaseEpFactory while later factories were still live. Load on the first factory and unload only after the last is released; roll back the refcount if the load fails so a retry re-attempts it. Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Cursor <cursoragent@cursor.com>
apwojcik
requested changes
Jun 18, 2026
apwojcik
left a comment
apwojcik
left a comment
Collaborator
There was a problem hiding this comment.
Can you please change hipep* to hipdnn* in the source directory name and the backend name as well? The backend name should not reveal that it is a standalone execution provider.
apwojcik
requested changes
Jun 18, 2026
| namespace { | ||
| constexpr auto directmlBackend{LIBRARY_PREFIX ORT_TSTR("directml-backend") LIBRARY_SUFFIX}; | ||
| constexpr auto migraphxBackend{LIBRARY_PREFIX ORT_TSTR("migraphx-backend") LIBRARY_SUFFIX}; | ||
| constexpr auto hipepBackend{LIBRARY_PREFIX ORT_TSTR("hipep-backend") LIBRARY_SUFFIX}; |
Collaborator
There was a problem hiding this comment.
Same here, please use hipdnnBackend instead of hipepBackend
Collaborator
There was a problem hiding this comment.
Alternatively, you may use hipBackend if it has nothing to do with DNN or anything else, but please do not include ep in backend names.
| # Copyright (c) Advanced Micro Devices, Inc. | ||
| # SPDX-License-Identifier: MIT | ||
|
|
||
| add_library(hipep-ep MODULE hipep_factory.cc) |
Collaborator
There was a problem hiding this comment.
Please use hipdnn-ep or hip-ep for the target name, not hipep.
| option(USE_AMDGPU "Build the AMD GPU Execution Provider" OFF) | ||
| option(USE_DML "Build the DirectML Execution Provider" OFF) | ||
| option(USE_MIGRAPHX "Build the MIGraphX Execution Provider" OFF) | ||
| option(USE_HIPEP "Build the HIP (morphizen) backend shim" OFF) |
Collaborator
There was a problem hiding this comment.
Please USE_HIPDNN or USE_HIP
| if(USE_AMDGPU) | ||
| set(CACHE{USE_DML} TYPE BOOL FORCE VALUE ON) | ||
| set(CACHE{USE_MIGRAPHX} TYPE BOOL FORCE VALUE ON) | ||
| set(CACHE{USE_HIPEP} TYPE BOOL FORCE VALUE ON) |
Collaborator
There was a problem hiding this comment.
Please do not include it in AMDGPU EP automatically yet. The HIPDNN backend has to be built on demand for now. Please reflect that in the source code. One has to be able to build AMDGPU EP without the HIP backend.
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
3 participants
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.
Add a
hipepbackend to the AMD GPU umbrella EP, selected via theprofile=llmprovider option.src/hipep/buildshipep-backend.dll, a thinOrtEpFactoryshim (parallel todirectml/migraphx) that loads the HIP EP DLL (hipep.dll), forwardsCreateEpFactories, and returns its factory unchanged. Single factory only.hipep-backendalongside the other backends and routesprofile=llmto it, passing no device (matching the DirectML/MIGraphX backends).related OGA PR: microsoft/onnxruntime-genai#2194