tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 04:15:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

add OP sigmoid (#12056)

Browse Source 
Co-authored-by: Judd <foldl@boxvest.com>
This commit is contained in:
Judd
2025-02-25 19:32:20 +08:00
committed by GitHub
parent 393fca629e
commit c132239bfb
3 changed files with 35 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@ -249,6 +249,7 @@ struct vk_device_struct {
vk_pipeline pipeline_relu_f32;
vk_pipeline pipeline_leaky_relu_f32;
vk_pipeline pipeline_tanh_f32;
vk_pipeline pipeline_sigmoid_f32;
vk_pipeline pipeline_diag_mask_inf_f32;
vk_pipeline pipeline_soft_max_f32, pipeline_soft_max_f32_f16;
vk_pipeline pipeline_soft_max_f32_wg512, pipeline_soft_max_f32_f16_wg512;
@ -2189,6 +2190,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
ggml_vk_create_pipeline(device, device->pipeline_relu_f32, "relu_f32", relu_f32_len, relu_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_leaky_relu_f32, "leaky_relu_f32", leaky_relu_f32_len, leaky_relu_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_tanh_f32, "tanh_f32", tanh_f32_len, tanh_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_sigmoid_f32, "sigmoid_f32", sigmoid_f32_len, sigmoid_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_diag_mask_inf_f32, "diag_mask_inf_f32", diag_mask_inf_f32_len, diag_mask_inf_f32_data, "main", 2, sizeof(vk_op_diag_mask_push_constants), {1, 512, 1}, {}, 1, true);
@ -5342,6 +5344,11 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
return ctx->device->pipeline_tanh_f32;
}
break;
case GGML_UNARY_OP_SIGMOID:
if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) {
return ctx->device->pipeline_sigmoid_f32;
}
break;
default:
break;
}
@ -7335,6 +7342,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_tensor * nod
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_RELU:
case GGML_UNARY_OP_TANH:
case GGML_UNARY_OP_SIGMOID:
break;
default:
return false;
@ -7551,6 +7559,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_tensor * nod
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_RELU:
case GGML_UNARY_OP_TANH:
case GGML_UNARY_OP_SIGMOID:
ggml_vk_unary(ctx, compute_ctx, src0, node, dryrun);
break;
default:
@ -7738,6 +7747,7 @@ static bool ggml_vk_compute_forward(ggml_backend_vk_context * ctx, ggml_tensor *
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_RELU:
case GGML_UNARY_OP_TANH:
case GGML_UNARY_OP_SIGMOID:
buf = tensor->buffer;
break;
default:
@ -8439,6 +8449,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
case GGML_UNARY_OP_SILU:
case GGML_UNARY_OP_RELU:
case GGML_UNARY_OP_TANH:
case GGML_UNARY_OP_SIGMOID:
return ggml_is_contiguous(op->src[0]);
default:
return false;
@ -9105,6 +9116,9 @@ static void ggml_vk_check_results_0(ggml_tensor * tensor) {
case GGML_UNARY_OP_TANH:
tensor_clone = ggml_tanh(ggml_ctx, src_clone[0]);
break;
case GGML_UNARY_OP_SIGMOID:
tensor_clone = ggml_sigmoid(ggml_ctx, src_clone[0]);
break;
default:
std::cerr << "Missing vk_check_results OP: " << ggml_op_name(tensor->op) << std::endl;
GGML_ABORT("fatal error");