Skip to content

[ET-VK] Support different input layouts in q8ta_binary operator #17563

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
meta-codesync merged 1 commit into from
Feb 20, 2026
+4 −1
Merged

[ET-VK] Support different input layouts in q8ta_binary operator #17563

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
3 changes: 2 additions & 1 deletion backends/vulkan/runtime/graph/ops/glsl/q8ta_binary.glsl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ layout(local_size_x_id = 0, local_size_y_id = 1, local_size_z_id = 2) in;

${layout_declare_spec_const(C, "int", "out_layout", "CONTIG_LAYOUT_INT")}
${layout_declare_spec_const(C, "int", "in_layout", "CONTIG_LAYOUT_INT")}
${layout_declare_spec_const(C, "int", "other_layout", "CONTIG_LAYOUT_INT")}
${layout_declare_spec_const(C, "int", "block_config", "0")}

// Generate loading functions for input buffers
Expand All @@ -71,7 +72,7 @@ void main() {
ivec4 in_block_a = load_int8x4_block_from_t_in_a(
in_a_meta, tidx, in_layout, block_outer_dim);
ivec4 in_block_b = load_int8x4_block_from_t_in_b(
in_b_meta, tidx, in_layout, block_outer_dim);
in_b_meta, tidx, other_layout, block_outer_dim);

ivec4 out_block;

Expand Down
2 changes: 2 additions & 0 deletions backends/vulkan/runtime/graph/ops/impl/Q8taBinary.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ void add_q8ta_binary_node(

VK_CHECK_COND(input_a_info.packed_dim == output_info.packed_dim);
VK_CHECK_COND(input_b_info.packed_dim == output_info.packed_dim);

VK_CHECK_COND(
input_a_info.packed_dim_block_size == output_info.packed_dim_block_size);
VK_CHECK_COND(
Expand Down Expand Up @@ -105,6 +106,7 @@ void add_q8ta_binary_node(
// Specialization Constants
{graph.hashed_layout_of(packed_int8_output),
graph.hashed_layout_of(packed_int8_input_a),
graph.hashed_layout_of(packed_int8_input_b),
block_config.as_packed_int()},
// Resize args
{block_config_ref},
Expand Down
Loading