Skip to content

Quantize Weight for Gemm/Conv on Quantized Model #22969

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

Merged
merged 5 commits into from
Jan 8, 2025
Merged

Quantize Weight for Gemm/Conv on Quantized Model #22969

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9389bbe
quantize weight
centwang Nov 28, 2024
aa00373
adjust ut scale and zp
centwang Nov 29, 2024
3c170c3
adjust ut data
centwang Nov 29, 2024
d8d1156
resolve comments
centwang Dec 4, 2024
e5b9b40
fix warn
centwang Dec 4, 2024
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
4 changes: 2 additions & 2 deletions onnxruntime/core/optimizer/graph_transformer_utils.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@
#ifdef MLAS_TARGET_AMD64_IX86
#include "core/optimizer/qdq_transformer/avx2_weight_s8_to_u8.h"
#endif
#include "core/optimizer/qdq_transformer/bias_quantization.h"
#include "core/optimizer/qdq_transformer/weight_bias_quantization.h"
#include "core/optimizer/qdq_transformer/clip_quantizelinear.h"
#include "core/optimizer/qdq_transformer/ensure_unique_dq_for_node_unit.h"
#include "core/optimizer/qdq_transformer/qdq_propagation.h"
Expand Down Expand Up @@ -244,7 +244,7 @@ InlinedVector<std::unique_ptr<GraphTransformer>> GenerateTransformers(

if (!disable_quant_qdq) {
transformers.emplace_back(std::make_unique<QDQPropagationTransformer>());
transformers.emplace_back(std::make_unique<BiasQuantization>());
transformers.emplace_back(std::make_unique<WeightBiasQuantization>());

// EnsureUniqueDQForNodeUnit is actually a required graph transformation. The unique DQ per QDQ node unit input
// condition that it ensures is important for the partitioning that happens after Level1 optimizers are run.
Expand Down
149 changes: 0 additions & 149 deletions onnxruntime/core/optimizer/qdq_transformer/bias_quantization.cc
View file
Open in desktop

This file was deleted.

27 changes: 0 additions & 27 deletions onnxruntime/core/optimizer/qdq_transformer/bias_quantization.h
View file
Open in desktop

This file was deleted.

Loading
Loading