mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-29 08:41:22 +00:00
@@ -423,7 +423,9 @@ struct llm_graph_params {
|
||||
(!ubatch.embd && !other.ubatch.embd)
|
||||
);
|
||||
|
||||
if (can_reuse_ubatch && !ubatch.equal_seqs()) {
|
||||
// when we split the batch using "equal_seqs" we have to verify that the participating sequences are the same
|
||||
// the reason is because the set of attention streams would be different for different sequences
|
||||
if (can_reuse_ubatch && ubatch.equal_seqs()) {
|
||||
if (!ubatch.data) {
|
||||
// if the old ubatch does not own it's data, then we cannot guarantee that it is still alive, and
|
||||
// therefore we cannot perform the sequence id check. normally should never happen
|
||||
|
||||
Reference in New Issue
Block a user