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

[webgpu] Only apply subgroup to intel gen-12lp #23377

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[webgpu] Only apply subgroup to intel gen-12lp #23377

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: 1 addition & 1 deletion onnxruntime/contrib_ops/webgpu/quantization/matmul_nbits.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -569,7 +569,7 @@ Status MatMulNBits::ComputeInternal(onnxruntime::webgpu::ComputeContext& context
// TODO: Support output_number > 1. Some cases are failed when output_number > 1.
constexpr uint32_t output_number = 1;
const uint32_t tile_m = M > kMinMForTileOptimization ? 4 : 1;
const bool use_subgroup = context.Device().HasFeature(wgpu::FeatureName::Subgroups) && context.AdapterInfo().vendor == std::string_view{"intel"} && components_a == 4 && block_size == 32;
const bool use_subgroup = context.Device().HasFeature(wgpu::FeatureName::Subgroups) && context.AdapterInfo().vendor == std::string_view{"intel"} && context.AdapterInfo().architecture == std::string_view{"gen-12lp"} && components_a == 4 && block_size == 32;
MatMulNBitsProgram program{output_number, block_size, tile_m, gsl::narrow<int>(components_b), has_zero_points, use_subgroup};
if (M > kMinMForTileOptimization && block_size == 32) {
components = 1;
Expand Down