happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

vulkan: support get_rows for i32 (#17941)

This commit is contained in:
Jeff Bolz 2025-12-13 03:12:53 -06:00 committed by GitHub
parent 3229a23fa6
commit 36255a2268
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 14 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@ -3738,6 +3738,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_IQ4_XS], "get_rows_iq4_xs", get_rows_iq4_xs_len, get_rows_iq4_xs_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_IQ4_NL], "get_rows_iq4_nl", get_rows_iq4_nl_len, get_rows_iq4_nl_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_MXFP4], "get_rows_mxfp4", get_rows_mxfp4_len, get_rows_mxfp4_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_I32], "get_rows_i32", get_rows_i32_len, get_rows_i32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_F32 ], "get_rows_f32_f32", get_rows_f32_f32_len, get_rows_f32_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), { 512, 1, 1}, {}, 1);
ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_F16 ], "get_rows_f16_f32", get_rows_f16_f32_len, get_rows_f16_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), { 512, 1, 1}, {}, 1);
@ -8294,6 +8295,11 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
switch (op) {
case GGML_OP_GET_ROWS:
GGML_ASSERT(src1->type == GGML_TYPE_I32);
if (src0->type == GGML_TYPE_I32) {
// i32 src only supports i32 result
GGML_ASSERT(dst->type == GGML_TYPE_I32);
return ctx->device->pipeline_get_rows[src0->type];
}
if (dst->type == GGML_TYPE_F16) {
return ctx->device->pipeline_get_rows[src0->type];
}
@ -13964,6 +13970,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
case GGML_TYPE_IQ4_XS:
case GGML_TYPE_IQ4_NL:
case GGML_TYPE_MXFP4:
case GGML_TYPE_I32:
return true;
default:
return false;

4
ggml/src/ggml-vulkan/vulkan-shaders/get_rows.comp
View File

@ -26,9 +26,9 @@ void main() {
const uint d_offset = get_doffset() + i10*p.nb21 + i11*p.nb22 + i12*p.nb23;
#if defined(DATA_A_BF16)
FLOAT_TYPE v = FLOAT_TYPE(bf16_to_fp32(data_a[a_offset + i00]));
TEMP_TYPE v = TEMP_TYPE(bf16_to_fp32(data_a[a_offset + i00]));
#else
FLOAT_TYPE v = FLOAT_TYPE(data_a[a_offset + i00]);
TEMP_TYPE v = TEMP_TYPE(data_a[a_offset + i00]);
#endif
#ifndef OPTIMIZATION_ERROR_WORKAROUND
data_d[d_offset + i00] = D_TYPE(v);

8
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
View File

@ -704,13 +704,15 @@ void process_shaders() {
shader = (tname == "f32" || tname == "f16" || tname == "bf16") ? "get_rows.comp" : "get_rows_quant.comp";
if (tname == "f16") {
string_to_spv("get_rows_" + tname, shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float16_t"}, {"OPTIMIZATION_ERROR_WORKAROUND", "1"}}));
string_to_spv("get_rows_" + tname, shader, merge_maps(base_dict, {{"TEMP_TYPE", "FLOAT_TYPE"}, {data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float16_t"}, {"OPTIMIZATION_ERROR_WORKAROUND", "1"}}));
} else {
string_to_spv("get_rows_" + tname, shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float16_t"}}));
string_to_spv("get_rows_" + tname, shader, merge_maps(base_dict, {{"TEMP_TYPE", "FLOAT_TYPE"}, {data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float16_t"}}));
}
string_to_spv("get_rows_" + tname + "_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float"}}));
string_to_spv("get_rows_" + tname + "_f32", shader, merge_maps(base_dict, {{"TEMP_TYPE", "FLOAT_TYPE"}, {data_a_key, "1"}, {"B_TYPE", "int"}, {"D_TYPE", "float"}}));
}
string_to_spv("get_rows_i32", "get_rows.comp", {{"TEMP_TYPE", "uint"}, {"A_TYPE", "uint"}, {"B_TYPE", "int"}, {"D_TYPE", "uint"}});
string_to_spv("mul_mat_vec_p021_f16_f32_subgroup_add", "mul_mat_vec_p021.comp", {{"A_TYPE", "float16_t"}, {"A_TYPE_VEC4", "f16vec4"}, {"B_TYPE", "float"}, {"B_TYPE_VEC4", "vec4"}, {"D_TYPE", "float"}, {"USE_SUBGROUP_ADD", "1"}});
string_to_spv("mul_mat_vec_p021_f16_f32", "mul_mat_vec_p021.comp", {{"A_TYPE", "float16_t"}, {"A_TYPE_VEC4", "f16vec4"}, {"B_TYPE", "float"}, {"B_TYPE_VEC4", "vec4"}, {"D_TYPE", "float"}});
string_to_spv("mul_mat_vec_nc_f16_f32", "mul_mat_vec_nc.comp", {{"A_TYPE", "float16_t"}, {"A_TYPE_VEC4", "f16vec4"}, {"B_TYPE", "float"}, {"B_TYPE_VEC4", "vec4"}, {"D_TYPE", "float"}});