vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

merge occam's https://github.com/ggml-org/llama.cpp/pull/14249

Browse source
This commit is contained in:
Concedo 2025-06-18 21:23:23 +08:00
parent 5f0a7a84ae
commit 9e49350507
1 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file

@ -9519,6 +9519,12 @@ static size_t ggml_backend_vk_host_buffer_type_get_alignment(ggml_backend_buffer
UNUSED(buft);
}
static size_t ggml_backend_vk_host_buffer_type_get_max_size(ggml_backend_buffer_type_t buft) {
return vk_instance.devices[0]->suballocation_block_size;
UNUSED(buft);
}
// Should be changed to return device-specific host buffer type
// but that probably requires changes in llama.cpp
ggml_backend_buffer_type_t ggml_backend_vk_host_buffer_type() {
@ -9527,7 +9533,7 @@ ggml_backend_buffer_type_t ggml_backend_vk_host_buffer_type() {
/* .get_name = */ ggml_backend_vk_host_buffer_type_name,
/* .alloc_buffer = */ ggml_backend_vk_host_buffer_type_alloc_buffer,
/* .get_alignment = */ ggml_backend_vk_host_buffer_type_get_alignment,
/* .get_max_size = */ NULL, // defaults to SIZE_MAX
/* .get_max_size = */ ggml_backend_vk_host_buffer_type_get_max_size,
/* .get_alloc_size = */ ggml_backend_cpu_buffer_type()->iface.get_alloc_size,
/* .is_host = */ ggml_backend_cpu_buffer_type()->iface.is_host,
},