Skip to content

Issue/1052: add functional per_tensor_quant_i8 API #1091

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
wooway777 merged 1 commit into from
Mar 18, 2026
Merged

Issue/1052: add functional per_tensor_quant_i8 API #1091

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions include/infinicore/ops/per_tensor_quant_i8.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,4 +8,6 @@ namespace infinicore::op {
INFINICORE_GRAPH_OP_CLASS(PerTensorQuantI8, const Tensor &, Tensor, Tensor, Tensor, bool);

void per_tensor_quant_i8_(const Tensor &x, Tensor x_packed, Tensor x_scale, Tensor x_zero, bool is_static);

Tensor per_tensor_quant_i8(const Tensor &x, Tensor x_scale, Tensor x_zero, bool is_static);
} // namespace infinicore::op
2 changes: 1 addition & 1 deletion include/infinicore/quantization/quantization_scheme.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ enum class QuantScheme {
AWQ_W4A16,
};

enum class KVQuantScheme {
enum class KVQuantAlgo {
NONE,
INT8,
};
Expand Down
6 changes: 6 additions & 0 deletions src/infinicore/ops/quant/per_tensor_quant_int8/per_tensor_quant_int8.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,4 +17,10 @@ void PerTensorQuantI8::execute(const Tensor &x, Tensor x_packed, Tensor x_scale,
void per_tensor_quant_i8_(const Tensor &x, Tensor x_packed, Tensor x_scale, Tensor x_zero, bool is_static) {
PerTensorQuantI8::execute(x, x_packed, x_scale, x_zero, is_static);
}

Tensor per_tensor_quant_i8(const Tensor &x, Tensor x_scale, Tensor x_zero, bool is_static) {
auto x_packed = Tensor::strided_empty(x->shape(), x->strides(), infinicore::DataType::I8, x->device());
PerTensorQuantI8::execute(x, x_packed, x_scale, x_zero, is_static);
return x_packed;
}
} // namespace infinicore::op
Loading