jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: add fast path for contiguous buffer transfers (#23973)

Browse Source
This commit is contained in:
Winston Ma 2026-06-11 21:46:25 +08:00 committed by GitHub
parent 1af154a76f
commit fdc3db9b65
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@ -7615,8 +7615,12 @@ static void ggml_vk_buffer_write_2d(vk_buffer& dst, size_t offset, const void *
if(dst->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible) {
GGML_ASSERT(dst->memory_property_flags & vk::MemoryPropertyFlagBits::eHostCoherent);
for (size_t i = 0; i < height; i++) {
memcpy((uint8_t *)dst->ptr + offset + i * dpitch, (const uint8_t *) src + i * spitch, width);
if (width == spitch && width == dpitch) {
memcpy((uint8_t *)dst->ptr + offset, src, width * height);
} else {
for (size_t i = 0; i < height; i++) {
memcpy((uint8_t *)dst->ptr + offset + i * dpitch, (const uint8_t *) src + i * spitch, width);
}
}
} else {
std::lock_guard<std::recursive_mutex> guard(dst->device->mutex);
@ -7735,8 +7739,12 @@ static void ggml_vk_buffer_read_2d(vk_buffer& src, size_t offset, void * dst, si
if(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible && src->device->uma) {
GGML_ASSERT(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostCoherent);
for (size_t i = 0; i < height; i++) {
memcpy((uint8_t *) dst + i * dpitch, (const uint8_t *) src->ptr + offset + i * spitch, width);
if (width == spitch && width == dpitch) {
memcpy(dst, (const uint8_t *) src->ptr + offset, width * height);
} else {
for (size_t i = 0; i < height; i++) {
memcpy((uint8_t *) dst + i * dpitch, (const uint8_t *) src->ptr + offset + i * spitch, width);
}
}
} else {
std::lock_guard<std::recursive_mutex> guard(src->device->mutex);