sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-01 22:54:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix double semicolon

Browse Source
This commit is contained in:
Ruben Ortlam
2026-03-24 13:57:56 +01:00
parent 63f85ed27e
commit df488da9ac
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@@ -1948,7 +1948,7 @@ static uint64_t vk_tensor_offset(const ggml_tensor * tensor) {
static uint32_t get_misalign_bytes(const ggml_backend_vk_context * ctx, const ggml_tensor * t)
{
return ((vk_tensor_offset(t) + t->view_offs) & (ctx->device->properties.limits.minStorageBufferOffsetAlignment - 1));;
return ((vk_tensor_offset(t) + t->view_offs) & (ctx->device->properties.limits.minStorageBufferOffsetAlignment - 1));
}
template <typename T> void init_pushconst_tensor_offsets(ggml_backend_vk_context * ctx, T &p, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, const ggml_tensor * src3, ggml_tensor * dst) {
@@ -7497,7 +7497,7 @@ static void ggml_vk_mul_mat_q_f16(ggml_backend_vk_context * ctx, vk_context& sub
const uint32_t split_k = ggml_vk_guess_split_k(ctx, ne01, ne11, ne10, disable_split_k, pipeline);
const uint64_t qx_sz = ggml_vk_repack_size_tensor(src0);;
const uint64_t qx_sz = ggml_vk_repack_size_tensor(src0);
const uint64_t qy_sz = ggml_type_size(src1->type) * y_ne / ggml_blck_size(src1->type);
const uint64_t x_sz = !qx_needs_dequant ? qx_sz : sizeof(ggml_fp16_t) * x_ne;
const uint64_t y_sz = quantize_y ? (ggml_vk_align_size(y_ne, 128) * ggml_type_size(GGML_TYPE_Q8_1) / ggml_blck_size(GGML_TYPE_Q8_1)) : (y_f32_kernel ? sizeof(float) * y_ne : sizeof(ggml_fp16_t) * y_ne);