mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-30 20:18:08 +00:00
fix the shared provider test for training build; expose more symbols to non cuda build (#8249)
* expose more symbols for non cuda build * fix the test execution provider for training build Co-authored-by: Cheng Tang <chenta@microsoft.com>
This commit is contained in:
Tang, Cheng
GitHub
parent
b46310b349
commit
996a98b3ac
6 changed files with 16 additions and 28 deletions
|
|
@ -1158,7 +1158,6 @@ if (NOT onnxruntime_ENABLE_TRAINING_TORCH_INTEROP)
|
|||
|
||||
# limit to only test on windows first, due to a runtime path issue on linux
|
||||
if (NOT onnxruntime_MINIMAL_BUILD AND NOT onnxruntime_EXTENDED_MINIMAL_BUILD
|
||||
AND NOT onnxruntime_ENABLE_TRAINING
|
||||
AND NOT ${CMAKE_SYSTEM_NAME} MATCHES "Darwin|iOS"
|
||||
AND NOT (CMAKE_SYSTEM_NAME STREQUAL "Android")
|
||||
AND NOT onnxruntime_BUILD_WEBASSEMBLY
|
||||
|
|
@ -1175,7 +1174,7 @@ if (NOT onnxruntime_ENABLE_TRAINING_TORCH_INTEROP)
|
|||
target_link_libraries(test_execution_provider PRIVATE onnxruntime_providers_shared)
|
||||
target_include_directories(test_execution_provider PRIVATE $<TARGET_PROPERTY:onnx,INTERFACE_INCLUDE_DIRECTORIES>)
|
||||
target_include_directories(test_execution_provider PRIVATE $<TARGET_PROPERTY:onnxruntime_common,INTERFACE_INCLUDE_DIRECTORIES>)
|
||||
target_include_directories(test_execution_provider PRIVATE ${ONNXRUNTIME_ROOT} ${CMAKE_CURRENT_BINARY_DIR})
|
||||
target_include_directories(test_execution_provider PRIVATE ${ONNXRUNTIME_ROOT} ${CMAKE_CURRENT_BINARY_DIR} ${ORTTRAINING_ROOT})
|
||||
if(APPLE)
|
||||
set_property(TARGET test_execution_provider APPEND_STRING PROPERTY LINK_FLAGS "-Xlinker -exported_symbols_list ${REPO_ROOT}/onnxruntime/test/testdata/custom_execution_provider_library/exported_symbols.lst")
|
||||
elseif(UNIX)
|
||||
|
|
|
|||
|
|
@ -779,6 +779,10 @@ struct ProviderHostImpl : ProviderHost {
|
|||
// AllocatorManager (direct)
|
||||
void AllocatorManager__InsertAllocator(AllocatorManager* p, AllocatorPtr allocator) override { p->AllocatorManager::InsertAllocator(allocator); }
|
||||
AllocatorPtr AllocatorManager__GetAllocator(const AllocatorManager* p, int id, OrtMemType mem_type) override { return p->AllocatorManager::GetAllocator(id, mem_type); };
|
||||
// From cpu/tensor/unsqueeze.h (direct)
|
||||
Status UnsqueezeBase__PrepareCompute(const UnsqueezeBase* p, OpKernelContext* ctx, UnsqueezeBase__Prepare& prepare) override { return p->UnsqueezeBase::PrepareCompute(ctx, reinterpret_cast<UnsqueezeBase::Prepare&>(prepare)); }
|
||||
// From cpu/tensor/gatherbase.h (direct)
|
||||
Status GatherBase__PrepareForCompute(const GatherBase* p, OpKernelContext* context, GatherBase__Prepare& prepare) override { return p->GatherBase::PrepareForCompute(context, reinterpret_cast<GatherBase::Prepare&>(prepare)); }
|
||||
|
||||
#ifdef USE_CUDA
|
||||
// GatherElements (direct)
|
||||
|
|
@ -801,8 +805,6 @@ struct ProviderHostImpl : ProviderHost {
|
|||
Status ValidateInputs(const Tensor* depth, const Tensor* values) override { return onnxruntime::ValidateInputs(depth, values); }
|
||||
Status PrepareOutputShape(const Tensor* indices, const int64_t depth_val, const int64_t axis, int64_t& prefix_dim_size, int64_t& suffix_dim_size, std::vector<int64_t>& output_shape) override { return onnxruntime::PrepareOutputShape(indices, depth_val, axis, prefix_dim_size, suffix_dim_size, output_shape); }
|
||||
|
||||
// From cpu/tensor/unsqueeze.h (direct)
|
||||
Status UnsqueezeBase__PrepareCompute(const UnsqueezeBase* p, OpKernelContext* ctx, UnsqueezeBase__Prepare& prepare) override { return p->UnsqueezeBase::PrepareCompute(ctx, reinterpret_cast<UnsqueezeBase::Prepare&>(prepare)); }
|
||||
// From cpu/tensor/slice.h (direct)
|
||||
Status SliceBase__PrepareForCompute(const std::vector<int64_t>& raw_starts,
|
||||
const std::vector<int64_t>& raw_ends,
|
||||
|
|
@ -837,9 +839,7 @@ struct ProviderHostImpl : ProviderHost {
|
|||
std::vector<int64_t>& split_sizes) override { return p->SplitBase::PrepareForCompute(input_shape, num_outputs, axis, before_dims, after_dims_including_split_axis, after_dims_excluding_split, split_sizes); }
|
||||
// From cpu/tensor/concatbase.h (direct)
|
||||
Status ConcatBase__PrepareForCompute(const ConcatBase* p, OpKernelContext* ctx, const std::vector<const Tensor*>& input_tensors, Prepare& prepare) override { return p->ConcatBase::PrepareForCompute(ctx, input_tensors, prepare); }
|
||||
// From cpu/tensor/gatherbase.h (direct)
|
||||
Status GatherBase__PrepareForCompute(const GatherBase* p, OpKernelContext* context, GatherBase__Prepare& prepare) override { return p->GatherBase::PrepareForCompute(context, reinterpret_cast<GatherBase::Prepare&>(prepare)); }
|
||||
|
||||
|
||||
PhiloxGenerator& PhiloxGenerator__Default() override { return PhiloxGenerator::Default(); }
|
||||
|
||||
Status Einsum__Compute(const Einsum* p, OpKernelContext* context) override { return p->Einsum::Compute(context); }
|
||||
|
|
|
|||
|
|
@ -379,6 +379,10 @@ Status UnpackTensor(const ONNX_NAMESPACE::TensorProto& tensor, const void* raw_d
|
|||
|
||||
} // namespace utils
|
||||
|
||||
Status GatherBase::PrepareForCompute(OpKernelContext* context, GatherBase::Prepare& p) const { return g_host->GatherBase__PrepareForCompute(this, context, reinterpret_cast<GatherBase__Prepare&>(p)); }
|
||||
Status UnsqueezeBase::PrepareCompute(OpKernelContext* ctx, UnsqueezeBase::Prepare& p) const { return g_host->UnsqueezeBase__PrepareCompute(this, ctx, reinterpret_cast<UnsqueezeBase__Prepare&>(p)); }
|
||||
|
||||
|
||||
#ifdef USE_CUDA
|
||||
bool TileOp::IsTileMemcpy(const TensorShape& input_shape, const int64_t* repeats, size_t rank, bool& is_batched_memcpy, size_t& num_of_elements_per_batch, size_t& num_of_copies_per_batch, size_t& num_of_batch_copies) {
|
||||
return g_host->TileOp__IsTileMemcpy(input_shape, repeats, rank, is_batched_memcpy, num_of_elements_per_batch, num_of_copies_per_batch, num_of_batch_copies);
|
||||
|
|
@ -387,8 +391,6 @@ bool TileOp::IsTileMemcpy(const TensorShape& input_shape, const int64_t* repeats
|
|||
Status NonMaxSuppressionBase::PrepareCompute(OpKernelContext* ctx, PrepareContext& pc) { return g_host->NonMaxSuppressionBase__PrepareCompute(ctx, pc); }
|
||||
Status NonMaxSuppressionBase::GetThresholdsFromInputs(const PrepareContext& pc, int64_t& max_output_boxes_per_class, float& iou_threshold, float& score_threshold) { return g_host->NonMaxSuppressionBase__GetThresholdsFromInputs(pc, max_output_boxes_per_class, iou_threshold, score_threshold); }
|
||||
|
||||
Status UnsqueezeBase::PrepareCompute(OpKernelContext* ctx, UnsqueezeBase::Prepare& p) const { return g_host->UnsqueezeBase__PrepareCompute(this, ctx, reinterpret_cast<UnsqueezeBase__Prepare&>(p)); }
|
||||
|
||||
Status SliceBase::PrepareForCompute(const std::vector<int64_t>& raw_starts,
|
||||
const std::vector<int64_t>& raw_ends,
|
||||
const std::vector<int64_t>& raw_axes,
|
||||
|
|
@ -424,8 +426,6 @@ Status PadBase::HandleDimValueZero(const Mode& mode, const TensorShape& input_sh
|
|||
Status ConcatBase::PrepareForCompute(OpKernelContext* ctx, const std::vector<const Tensor*>& input_tensors,
|
||||
Prepare& p) const { return g_host->ConcatBase__PrepareForCompute(this, ctx, input_tensors, p); }
|
||||
|
||||
Status GatherBase::PrepareForCompute(OpKernelContext* context, GatherBase::Prepare& p) const { return g_host->GatherBase__PrepareForCompute(this, context, reinterpret_cast<GatherBase__Prepare&>(p)); }
|
||||
|
||||
PhiloxGenerator& PhiloxGenerator::Default() { return g_host->PhiloxGenerator__Default(); }
|
||||
|
||||
Status Einsum::Compute(OpKernelContext* context) const { return g_host->Einsum__Compute(this, context); }
|
||||
|
|
|
|||
|
|
@ -692,6 +692,10 @@ struct ProviderHost {
|
|||
// AllocatorManager
|
||||
virtual void AllocatorManager__InsertAllocator(AllocatorManager* p, AllocatorPtr allocator) = 0;
|
||||
virtual AllocatorPtr AllocatorManager__GetAllocator(const AllocatorManager* p, int id, OrtMemType mem_type) = 0;
|
||||
// From cpu/tensor/unsqueeze.h
|
||||
virtual Status UnsqueezeBase__PrepareCompute(const UnsqueezeBase* p, OpKernelContext* ctx, UnsqueezeBase__Prepare& prepare) = 0;
|
||||
// From cpu/tensor/gatherbase.h
|
||||
virtual Status GatherBase__PrepareForCompute(const GatherBase* p, OpKernelContext* context, GatherBase__Prepare& prepare) = 0;
|
||||
|
||||
#ifdef USE_CUDA
|
||||
// GatherElements
|
||||
|
|
@ -714,8 +718,6 @@ struct ProviderHost {
|
|||
virtual Status ValidateInputs(const Tensor* depth, const Tensor* values) = 0;
|
||||
virtual Status PrepareOutputShape(const Tensor* indices, const int64_t depth_val, const int64_t axis, int64_t& prefix_dim_size, int64_t& suffix_dim_size, std::vector<int64_t>& output_shape) = 0;
|
||||
|
||||
// From cpu/tensor/unsqueeze.h
|
||||
virtual Status UnsqueezeBase__PrepareCompute(const UnsqueezeBase* p, OpKernelContext* ctx, UnsqueezeBase__Prepare& prepare) = 0;
|
||||
// From cpu/tensor/slice.h
|
||||
virtual Status SliceBase__PrepareForCompute(const std::vector<int64_t>& raw_starts,
|
||||
const std::vector<int64_t>& raw_ends,
|
||||
|
|
@ -749,9 +751,7 @@ struct ProviderHost {
|
|||
std::vector<int64_t>& split_sizes) = 0;
|
||||
// From cpu/tensor/concatbase.h
|
||||
virtual Status ConcatBase__PrepareForCompute(const ConcatBase* p, OpKernelContext* ctx, const std::vector<const Tensor*>& input_tensors, Prepare& prepare) = 0;
|
||||
// From cpu/tensor/gatherbase.h
|
||||
virtual Status GatherBase__PrepareForCompute(const GatherBase* p, OpKernelContext* context, GatherBase__Prepare& prepare) = 0;
|
||||
|
||||
|
||||
virtual PhiloxGenerator& PhiloxGenerator__Default() = 0;
|
||||
|
||||
virtual Status Einsum__Compute(const Einsum* p, OpKernelContext* context) = 0;
|
||||
|
|
|
|||
|
|
@ -1680,7 +1680,7 @@ void CreatePybindStateModule(py::module& m) {
|
|||
addOrtValueMethods(m);
|
||||
addIoBindingMethods(m);
|
||||
|
||||
#if !defined(ENABLE_TRAINING) && !defined(__APPLE__) && \
|
||||
#if !defined(__APPLE__) && \
|
||||
(!defined(ORT_MINIMAL_BUILD) || defined(ORT_EXTENDED_MINIMAL_BUILD) || defined(ORT_MINIMAL_BUILD_CUSTOM_OPS))
|
||||
Ort::SessionOptions tmp_options;
|
||||
if (!InitProvidersSharedLibrary()) {
|
||||
|
|
|
|||
|
|
@ -963,17 +963,6 @@ class TestInferenceSession(unittest.TestCase):
|
|||
if not sys.platform.startswith("win"):
|
||||
return
|
||||
|
||||
# Exclude for training
|
||||
training_enabled = False
|
||||
try:
|
||||
from onnxruntime.capi.ort_trainer import ORTTrainer
|
||||
training_enabled = True
|
||||
except:
|
||||
pass
|
||||
|
||||
if training_enabled:
|
||||
return
|
||||
|
||||
shared_library = 'test_execution_provider.dll'
|
||||
if not os.path.exists(shared_library):
|
||||
raise FileNotFoundError("Unable to find '{0}'".format(shared_library))
|
||||
|
|
|
|||
Loading…
Reference in a new issue