Skip to content

ggml: allow backend inputs to not create another split #28387

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
am17an wants to merge 1 commit into
base: master
Choose a base branch
from
+2 −13
Open

ggml: allow backend inputs to not create another split #28387

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
15 changes: 2 additions & 13 deletions ggml/src/ggml-backend.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -849,7 +849,7 @@ static void ggml_backend_sched_split_inputs_grow(struct ggml_backend_sched_split
int new_cap = GGML_SCHED_MAX_SPLIT_INPUTS;
if (split->inputs_capacity > 0) {
new_cap = 2*split->inputs_capacity;
GGML_LOG_WARN("%s: increasing split inputs capacity from %d to %d\n", __func__, split->inputs_capacity, new_cap);
GGML_LOG_DEBUG("%s: increasing split inputs capacity from %d to %d\n", __func__, split->inputs_capacity, new_cap);
}
auto * pnew = (struct ggml_tensor **) realloc((void *) split->inputs, new_cap * sizeof(struct ggml_tensor *));
if (pnew == NULL) {
Expand All @@ -864,7 +864,7 @@ static void ggml_backend_sched_graph_inputs_grow(ggml_backend_sched_t sched) {
int new_cap = GGML_SCHED_MAX_SPLIT_INPUTS;
if (sched->graph_inputs_capacity > 0) {
new_cap = 2*sched->graph_inputs_capacity;
GGML_LOG_WARN("%s: increasing graph inputs capacity from %d to %d\n", __func__, sched->graph_inputs_capacity, new_cap);
GGML_LOG_DEBUG("%s: increasing graph inputs capacity from %d to %d\n", __func__, sched->graph_inputs_capacity, new_cap);
}
auto * pnew = (struct ggml_tensor **) realloc((void *) sched->graph_inputs, new_cap * sizeof(struct ggml_tensor *));
if (pnew == NULL) {
Expand Down Expand Up @@ -1338,17 +1338,6 @@ void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct ggml_cgra
break;
}
}
// check if the split has too many inputs
// FIXME: count the number of inputs instead of only checking when full
if (split->n_inputs >= split->inputs_capacity) {
const size_t id = hash_id(src);
int src_backend_id = sched->hv_tensor_backend_ids[id];
bool supported = ggml_backend_sched_buffer_supported(sched, src, cur_backend_id);
if (src_backend_id != cur_backend_id && tensor_id_copy(id, cur_backend_id, 0) == NULL && !supported) {
need_new_split = true;
break;
}
}
}
}

Expand Down
Loading