Skip to content

perf: allocate CPU-offloaded params from runtime device pinned host buffer #1601

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
fszontagh wants to merge 1 commit into
base: master
Choose a base branch
from
+12 −1
Open

perf: allocate CPU-offloaded params from runtime device pinned host buffer #1601

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion src/ggml_extend.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3017,7 +3017,18 @@ struct GGMLRunner {
LOG_DEBUG("%s skipping params allocation (no tensors)", get_desc().c_str());
return true;
}
params_buffer = ggml_backend_alloc_ctx_tensors(params_ctx, params_backend);
// Pinned host buffer when CPU-offloaded for DMA-direct H2D.
ggml_backend_buffer_type_t params_buft = nullptr;
if (params_backend != runtime_backend) {
ggml_backend_dev_t runtime_dev = ggml_backend_get_device(runtime_backend);
if (runtime_dev != nullptr) {
params_buft = ggml_backend_dev_host_buffer_type(runtime_dev);
}
}
if (params_buft == nullptr) {
params_buft = ggml_backend_get_default_buffer_type(params_backend);
}
params_buffer = ggml_backend_alloc_ctx_tensors_from_buft(params_ctx, params_buft);
if (params_buffer == nullptr) {
LOG_ERROR("%s alloc params backend buffer failed, num_tensors = %i",
get_desc().c_str(),
Expand Down
Loading