Skip to content

vulkan: skip unused RMSNorm fallback pipelines #7133

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
nihui merged 1 commit into from
Oct 18, 2026
Merged

vulkan: skip unused RMSNorm fallback pipelines #7133

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
105 changes: 54 additions & 51 deletions src/layer/vulkan/rmsnorm_vulkan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,49 +45,65 @@ int RMSNorm_vulkan::create_pipeline(const Option& opt)
// sanitize wired subgroup_size
use_subgroup_ops = false;
}
// Reuse the LN reduce_sum4 / reduce_mean size and local workgroup configuration [from LN code].
// square: only compute x^2; coeffs: a = 1 / sqrt(rms + eps); norm: v = v * a; (if affine: v *= gamma)
if (use_subgroup_ops)
{
pipeline_rmsnorm_square = new Pipeline(vkdev);
pipeline_rmsnorm_square->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_square->create(LayerShaderType::rmsnorm_square, opt, std::vector<vk_specialization_type>());
pipeline_rmsnorm_reduce_subgroup = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_subgroup->set_subgroup_size(subgroup_size);
pipeline_rmsnorm_reduce_subgroup->set_local_size_xyz(subgroup_size, 1, 1);
pipeline_rmsnorm_reduce_subgroup->create(LayerShaderType::rmsnorm_reduce_subgroup, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_square_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_square_pack4->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_square_pack4->create(LayerShaderType::rmsnorm_square_pack4, opt, std::vector<vk_specialization_type>());
pipeline_rmsnorm_reduce_subgroup_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_subgroup_pack4->set_subgroup_size(subgroup_size);
pipeline_rmsnorm_reduce_subgroup_pack4->set_local_size_xyz(subgroup_size, 1, 1);
pipeline_rmsnorm_reduce_subgroup_pack4->create(LayerShaderType::rmsnorm_reduce_subgroup_pack4, opt, std::vector<vk_specialization_type>());
}
else
{
// Same as LN's reduce_sum4 (first pass fp16->fp32, then iterative fp32 passes alternating between two pipelines) and reduce_mean (see LN).
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32->set_optimal_local_size_xyz(16, 4, 1);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32->create(LayerShaderType::layernorm_reduce_sum4_fp16_to_fp32, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_sum4_fp32[0] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32[0]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32[0]->create(LayerShaderType::layernorm_reduce_sum4_fp32, opt, std::vector<vk_specialization_type>());
pipeline_rmsnorm_reduce_sum4_fp32[1] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32[1]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32[1]->create(LayerShaderType::layernorm_reduce_sum4_fp32, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_sum4_fp16_to_fp32_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32_pack4->set_optimal_local_size_xyz(16, 4, 1);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32_pack4->create(LayerShaderType::layernorm_reduce_sum4_fp16_to_fp32_pack4, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_sum4_fp32_pack4[0] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[0]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[0]->create(LayerShaderType::layernorm_reduce_sum4_fp32_pack4, opt, std::vector<vk_specialization_type>());
pipeline_rmsnorm_reduce_sum4_fp32_pack4[1] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[1]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[1]->create(LayerShaderType::layernorm_reduce_sum4_fp32_pack4, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_mean = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_mean->set_optimal_local_size_xyz(1, 8, 8);
pipeline_rmsnorm_reduce_mean->create(LayerShaderType::layernorm_reduce_mean, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_mean_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_mean_pack4->set_optimal_local_size_xyz(1, 8, 8);
pipeline_rmsnorm_reduce_mean_pack4->create(LayerShaderType::layernorm_reduce_mean_pack4, opt, std::vector<vk_specialization_type>());
// Reuse the LN reduce_sum4 / reduce_mean size and local workgroup configuration [from LN code].
// square: only compute x^2; coeffs: a = 1 / sqrt(rms + eps); norm: v = v * a; (if affine: v *= gamma)
{
pipeline_rmsnorm_square = new Pipeline(vkdev);
pipeline_rmsnorm_square->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_square->create(LayerShaderType::rmsnorm_square, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_square_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_square_pack4->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_square_pack4->create(LayerShaderType::rmsnorm_square_pack4, opt, std::vector<vk_specialization_type>());
}
{
// Same as LN's reduce_sum4 (first pass fp16->fp32, then iterative fp32 passes alternating between two pipelines) and reduce_mean (see LN).
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32->set_optimal_local_size_xyz(16, 4, 1);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32->create(LayerShaderType::layernorm_reduce_sum4_fp16_to_fp32, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_sum4_fp32[0] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32[0]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32[0]->create(LayerShaderType::layernorm_reduce_sum4_fp32, opt, std::vector<vk_specialization_type>());
pipeline_rmsnorm_reduce_sum4_fp32[1] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32[1]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32[1]->create(LayerShaderType::layernorm_reduce_sum4_fp32, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_sum4_fp16_to_fp32_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32_pack4->set_optimal_local_size_xyz(16, 4, 1);
pipeline_rmsnorm_reduce_sum4_fp16_to_fp32_pack4->create(LayerShaderType::layernorm_reduce_sum4_fp16_to_fp32_pack4, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_sum4_fp32_pack4[0] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[0]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[0]->create(LayerShaderType::layernorm_reduce_sum4_fp32_pack4, opt, std::vector<vk_specialization_type>());
pipeline_rmsnorm_reduce_sum4_fp32_pack4[1] = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[1]->set_optimal_local_size_xyz(8, 8, 1);
pipeline_rmsnorm_reduce_sum4_fp32_pack4[1]->create(LayerShaderType::layernorm_reduce_sum4_fp32_pack4, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_mean = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_mean->set_optimal_local_size_xyz(1, 8, 8);
pipeline_rmsnorm_reduce_mean->create(LayerShaderType::layernorm_reduce_mean, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_mean_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_mean_pack4->set_optimal_local_size_xyz(1, 8, 8);
pipeline_rmsnorm_reduce_mean_pack4->create(LayerShaderType::layernorm_reduce_mean_pack4, opt, std::vector<vk_specialization_type>());
}
}

{
// coeffs: only eps is used as a specialization constant
std::vector<vk_specialization_type> spec(1);
Expand Down Expand Up @@ -116,19 +132,6 @@ int RMSNorm_vulkan::create_pipeline(const Option& opt)
pipeline_rmsnorm_norm_pack4->create(LayerShaderType::rmsnorm_norm_pack4, opt, spec);
}

if (use_subgroup_ops)
{
pipeline_rmsnorm_reduce_subgroup = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_subgroup->set_subgroup_size(subgroup_size);
pipeline_rmsnorm_reduce_subgroup->set_local_size_xyz(subgroup_size, 1, 1);
pipeline_rmsnorm_reduce_subgroup->create(LayerShaderType::rmsnorm_reduce_subgroup, opt, std::vector<vk_specialization_type>());

pipeline_rmsnorm_reduce_subgroup_pack4 = new Pipeline(vkdev);
pipeline_rmsnorm_reduce_subgroup_pack4->set_subgroup_size(subgroup_size);
pipeline_rmsnorm_reduce_subgroup_pack4->set_local_size_xyz(subgroup_size, 1, 1);
pipeline_rmsnorm_reduce_subgroup_pack4->create(LayerShaderType::rmsnorm_reduce_subgroup_pack4, opt, std::vector<vk_specialization_type>());
}

return 0;
}

Expand Down
Loading