sleepy/llama.cpp
1
0
Fork 0
Code Issues 16 Pull Requests Actions 163 Packages Projects Releases Wiki Activity

vulkan: support GGML_OP_DIAG (#17893)

Browse Source
This commit is contained in:
Jeff Bolz
2025-12-13 03:07:49 -06:00
committed by GitHub
parent 303f8615e9
commit 3229a23fa6
3 changed files with 55 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-vulkan/ggml-vulkan.cpp
+24
View File
@@ -659,6 +659,7 @@ struct vk_device_struct {
vk_pipeline pipeline_cos_f32;
vk_pipeline pipeline_log[2];
vk_pipeline pipeline_tri[2];
vk_pipeline pipeline_diag[2];
vk_pipeline pipeline_clamp_f32;
vk_pipeline pipeline_pad_f32;
vk_pipeline pipeline_roll_f32;
@@ -3924,6 +3925,9 @@ static void ggml_vk_load_shaders(vk_device& device) {
ggml_vk_create_pipeline(device, device->pipeline_tri[0], "tri_f32", tri_f32_len, tri_f32_data, "main", 2, sizeof(vk_op_unary_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_tri[1], "tri_f16", tri_f16_len, tri_f16_data, "main", 2, sizeof(vk_op_unary_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_diag[0], "diag_f32", diag_f32_len, diag_f32_data, "main", 2, sizeof(vk_op_unary_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_diag[1], "diag_f16", diag_f16_len, diag_f16_data, "main", 2, sizeof(vk_op_unary_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_clamp_f32, "clamp_f32", clamp_f32_len, clamp_f32_data, "main", 2, sizeof(vk_op_unary_push_constants), {512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_pad_f32, "pad_f32", pad_f32_len, pad_f32_data, "main", 2, sizeof(vk_op_pad_push_constants), {512, 1, 1}, {}, 1);
@@ -8416,6 +8420,12 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
return ctx->device->pipeline_tri[dst->type == GGML_TYPE_F16];
}
return nullptr;
case GGML_OP_DIAG:
if (src0->type == dst->type &&
(src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16)) {
return ctx->device->pipeline_diag[dst->type == GGML_TYPE_F16];
}
return nullptr;
case GGML_OP_CLAMP:
if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) {
return ctx->device->pipeline_clamp_f32;
@@ -9109,6 +9119,7 @@ static void ggml_vk_op_f32(ggml_backend_vk_context * ctx, vk_context& subctx, co
case GGML_OP_COS:
case GGML_OP_LOG:
case GGML_OP_TRI:
case GGML_OP_DIAG:
case GGML_OP_CLAMP:
case GGML_OP_PAD:
case GGML_OP_ROLL:
@@ -9796,6 +9807,12 @@ static void ggml_vk_tri(ggml_backend_vk_context * ctx, vk_context& subctx, const
ggml_vk_op_f32(ctx, subctx, src0, nullptr, nullptr, nullptr, dst, GGML_OP_TRI, std::move(p));
}
static void ggml_vk_diag(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst) {
vk_op_unary_push_constants p = vk_op_unary_push_constants_init(src0, dst, ggml_nelements(dst));
ggml_vk_op_f32(ctx, subctx, src0, nullptr, nullptr, nullptr, dst, GGML_OP_DIAG, std::move(p));
}
static void ggml_vk_clamp(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst) {
vk_op_unary_push_constants p = vk_op_unary_push_constants_init(src0, dst);
p.param1 = ggml_get_op_params_f32(dst, 0);
@@ -11924,6 +11941,10 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_cgraph * cgr
case GGML_OP_TRI:
ggml_vk_tri(ctx, compute_ctx, src0, node);
break;
case GGML_OP_DIAG:
ggml_vk_diag(ctx, compute_ctx, src0, node);
break;
case GGML_OP_CLAMP:
ggml_vk_clamp(ctx, compute_ctx, src0, node);
@@ -14067,6 +14088,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
return ggml_is_contiguous(op->src[0]) && op->src[0]->type == GGML_TYPE_F32;
case GGML_OP_LOG:
case GGML_OP_TRI:
case GGML_OP_DIAG:
return (op->src[0]->type == GGML_TYPE_F32 || op->src[0]->type == GGML_TYPE_F16) &&
op->type == op->src[0]->type;
case GGML_OP_ARGSORT:
@@ -14657,6 +14679,8 @@ static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph *
tensor_clone = ggml_log(ggml_ctx, src_clone[0]);
} else if (tensor->op == GGML_OP_TRI) {
tensor_clone = ggml_tri(ggml_ctx, src_clone[0], ggml_get_op_params_i32(tensor, 0));
} else if (tensor->op == GGML_OP_DIAG) {
tensor_clone = ggml_diag(ggml_ctx, src_clone[0]);
} else if (tensor->op == GGML_OP_CLAMP) {
const float * params = (const float *)tensor->op_params;
tensor_clone = ggml_clamp(ggml_ctx, src_clone[0], params[0], params[1]);