root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Enable use to the rebar feature to upload buffers to the device. (#9251)

Browse Source
This commit is contained in:
Markus Tavenrath 2024-09-28 12:05:05 +02:00 committed by GitHub
parent b5de3b74a5
commit 89f9944981
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
ggml/src/ggml-vulkan.cpp
View File

@ -1079,7 +1079,8 @@ static vk_buffer ggml_vk_create_buffer_device(vk_device& device, size_t size) {
// Fall back to host memory type
buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eDeviceLocal, vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent);
} else {
buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eDeviceLocal);
// use rebar if available, otherwise fallback to device only visible memory
buf = ggml_vk_create_buffer(device, size, vk::MemoryPropertyFlagBits::eDeviceLocal | vk::MemoryPropertyFlagBits::eHostVisible | vk::MemoryPropertyFlagBits::eHostCoherent, vk::MemoryPropertyFlagBits::eDeviceLocal);
}
} catch (const vk::SystemError& e) {
std::cerr << "ggml_vulkan: Device memory allocation of size " << size << " failed." << std::endl;
@ -2806,7 +2807,11 @@ static void ggml_vk_buffer_read_async(vk_context subctx, vk_buffer& src, size_t
static void ggml_vk_buffer_read(vk_buffer& src, size_t offset, void * dst, size_t size) {
VK_LOG_DEBUG("ggml_vk_buffer_read(" << src->buffer << ", " << offset << ", " << size << ")");
if(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible) {
// If the device is not an UMA device the memory is host-accessible through rebar. While writing
// through PCIe is sufficient fast reading back data from PCIe is slower than going through
// the HW device to host copy path.
if(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostVisible && src->device->uma) {
GGML_ASSERT(src->memory_property_flags & vk::MemoryPropertyFlagBits::eHostCoherent);
memcpy(dst, (uint8_t *) src->ptr + offset, size);