mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 34 Packages Projects Releases Wiki Activity

llama : disable graph reuse with pipeline parallelism (#20463)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-03-12 21:04:13 +02:00
committed by GitHub
parent 557fe2d913
commit 57819b8d4b
3 changed files with 17 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-backend.cpp
+5 -9
View File
@@ -1455,10 +1455,6 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s
int split_backend_id = split->backend_id;
ggml_backend_t split_backend = sched->backends[split_backend_id];
if (sched->events[split_backend_id][sched->cur_copy] == NULL) {
ggml_backend_synchronize(split_backend);
}
// copy the input tensors to the split backend
for (int input_id = 0; input_id < split->n_inputs; input_id++) {
ggml_backend_t input_backend = ggml_backend_sched_get_tensor_backend(sched, split->inputs[input_id]);
@@ -1469,12 +1465,16 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s
// inputs from the user must be copied immediately to prevent the user overwriting the data before the copy is done
if (sched->events[split_backend_id][sched->cur_copy] != NULL) {
ggml_backend_event_synchronize(sched->events[split_backend_id][sched->cur_copy]);
} else {
ggml_backend_synchronize(split_backend);
}
ggml_backend_tensor_copy_async(input_backend, split_backend, input, input_cpy);
ggml_backend_tensor_copy(input, input_cpy);
} else {
// wait for the split backend to finish using the input before overwriting it
if (sched->events[split_backend_id][sched->cur_copy] != NULL) {
ggml_backend_event_wait(split_backend, sched->events[split_backend_id][sched->cur_copy]);
} else {
ggml_backend_synchronize(split_backend);
}
// when offloading MoE weights, we can reduce the amount of data copied by copying only the experts that are used
@@ -1578,10 +1578,6 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t s
}
}
if (sched->events[split_backend_id][sched->cur_copy] == NULL) {
ggml_backend_synchronize(split_backend);
}
if (!sched->callback_eval) {
enum ggml_status ec = ggml_backend_graph_compute_async(split_backend, &split->graph);
if (ec != GGML_STATUS_SUCCESS) {