Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix onnx BQ segfaults with large models #3459

Merged
merged 1 commit into from
Nov 1, 2024
Merged

Fix onnx BQ segfaults with large models #3459

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions TrainingExtensions/onnx/src/QuantizeDequantizeUtils.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,13 +198,14 @@ void quantizeDequantizeBroadcast(const T* inTensor, T* outTensor, const Broadcas
const int64_t* encodingStrides = shapeInfo.encodingStrides.data();

// Kernels expect separate lists for each encoding type
T encVec[4][numEncodings];
std::vector<T> encVec(4 * numEncodings);

for (int i = 0; i < numEncodings; i++)
{
encVec[0][i] = encodings[i]->min;
encVec[1][i] = encodings[i]->max;
encVec[2][i] = encodings[i]->delta;
encVec[3][i] = encodings[i]->offset;
encVec[i] = encodings[i]->min;
encVec[numEncodings + i] = encodings[i]->max;
encVec[2 * numEncodings + i] = encodings[i]->delta;
encVec[3 * numEncodings + i] = encodings[i]->offset;
}
T* encodingVectorDevice;
int64_t* stridesDevice = nullptr;
Expand All @@ -217,7 +218,7 @@ void quantizeDequantizeBroadcast(const T* inTensor, T* outTensor, const Broadcas
encodingVectorDevice = static_cast<T*>(allocator->allocateRaw(4 * numEncodings * sizeof(T)));

// Send encoding information to device
cudaMemcpyAsync(encodingVectorDevice, encVec, 4 * numEncodings * sizeof(T), cudaMemcpyHostToDevice,
cudaMemcpyAsync(encodingVectorDevice, encVec.data(), 4 * numEncodings * sizeof(T), cudaMemcpyHostToDevice,
static_cast<cudaStream_t>(stream));

// Send stride information to device
Expand All @@ -237,7 +238,7 @@ void quantizeDequantizeBroadcast(const T* inTensor, T* outTensor, const Broadcas
else
{
mode = DlQuantization::ComputationMode::COMP_MODE_CPU;
encodingVectorDevice = (T*) (encVec);
encodingVectorDevice = encVec.data();
}

T* encodingMin = encodingVectorDevice;
Expand Down
Loading