vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 01:54:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

ggml : fix fallback to CPU for ununsupported ops (#15118)

Browse source
This commit is contained in:
Diego Devesa 2025-08-06 05:37:35 -07:00 • committed by GitHub
parent 65c797c4fa
commit 0d8831543c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 27 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

9
ggml/src/ggml-backend.cpp
View file

@ -1071,6 +1071,11 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg
}
}
}
// if the node is still unassigned, assign it to the first backend that supports it
for (int b = 0; b < sched->n_backends && *cur_backend_id == -1; b++) {
ggml_backend_sched_set_if_supported(sched, node, b, cur_backend_id);
}
GGML_ASSERT(*cur_backend_id != -1);
}
// pass 5: split graph, find tensors that need to be copied
@ -1098,7 +1103,7 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg
const int node_backend_id = tensor_backend_id(node);
assert(node_backend_id != -1); // all nodes should be assigned by now, this can happen if there is no CPU fallback
GGML_ASSERT(node_backend_id != -1); // all nodes should be assigned by now, this can happen if there is no CPU fallback
// check if we should start a new split based on the sources of the current node
bool need_new_split = false;
@ -1156,7 +1161,7 @@ static void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct gg
size_t src_id = hash_id(src);
const int src_backend_id = sched->hv_tensor_backend_ids[src_id];
assert(src_backend_id != -1); // all inputs should be assigned by now
GGML_ASSERT(src_backend_id != -1); // all inputs should be assigned by now
if (src->flags & GGML_TENSOR_FLAG_INPUT && sched->n_copies > 1) {
if (tensor_id_copy(src_id, src_backend_id, 0) == NULL) {