CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

add GELU_ERF (#14455)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-07-01 10:14:21 +02:00
committed by GitHub
parent a6a47958a1
commit eff5e45443
3 changed files with 52 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@@ -431,6 +431,7 @@ struct vk_device_struct {
// [src/dst 0=fp32,1=fp16]
vk_pipeline pipeline_gelu[2];
vk_pipeline pipeline_gelu_erf[2];
vk_pipeline pipeline_gelu_quick[2];
vk_pipeline pipeline_silu[2];
vk_pipeline pipeline_relu[2];
@@ -2761,6 +2762,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
ggml_vk_create_pipeline(device, device->pipeline_ ## name [1], #name "_f16", name ## _f16_len, name ## _f16_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
CREATE_UNARY(gelu)
CREATE_UNARY(gelu_erf)
CREATE_UNARY(gelu_quick)
CREATE_UNARY(silu)
CREATE_UNARY(relu)
@@ -6481,6 +6483,8 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
return ctx->device->pipeline_silu[dst->type == GGML_TYPE_F16];
case GGML_UNARY_OP_GELU:
return ctx->device->pipeline_gelu[dst->type == GGML_TYPE_F16];
case GGML_UNARY_OP_GELU_ERF:
return ctx->device->pipeline_gelu_erf[dst->type == GGML_TYPE_F16];
case GGML_UNARY_OP_GELU_QUICK:
return ctx->device->pipeline_gelu_quick[dst->type == GGML_TYPE_F16];
case GGML_UNARY_OP_RELU:
@@ -8827,6 +8831,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_cgraph * cgr
switch (ggml_get_unary_op(node)) {
case GGML_UNARY_OP_SILU:
case GGML_UNARY_OP_GELU:
case GGML_UNARY_OP_GELU_ERF:
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_RELU:
case GGML_UNARY_OP_TANH:
@@ -9072,6 +9077,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_cgraph * cgr
switch (ggml_get_unary_op(node)) {
case GGML_UNARY_OP_SILU:
case GGML_UNARY_OP_GELU:
case GGML_UNARY_OP_GELU_ERF:
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_RELU:
case GGML_UNARY_OP_TANH:
@@ -9289,6 +9295,7 @@ static bool ggml_vk_compute_forward(ggml_backend_vk_context * ctx, ggml_tensor *
switch (ggml_get_unary_op(tensor)) {
case GGML_UNARY_OP_SILU:
case GGML_UNARY_OP_GELU:
case GGML_UNARY_OP_GELU_ERF:
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_RELU:
case GGML_UNARY_OP_TANH:
@@ -10095,6 +10102,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
case GGML_OP_UNARY:
switch (ggml_get_unary_op(op)) {
case GGML_UNARY_OP_GELU:
case GGML_UNARY_OP_GELU_ERF:
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_SILU:
case GGML_UNARY_OP_RELU:
@@ -10835,6 +10843,9 @@ static void ggml_vk_check_results_0(ggml_tensor * tensor) {
case GGML_UNARY_OP_GELU:
tensor_clone = ggml_gelu(ggml_ctx, src_clone[0]);
break;
case GGML_UNARY_OP_GELU_ERF:
tensor_clone = ggml_gelu_erf(ggml_ctx, src_clone[0]);
break;
case GGML_UNARY_OP_GELU_QUICK:
tensor_clone = ggml_gelu_quick(ggml_ctx, src_clone[0]);
break;