CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

memory : fix broken batch splits for recurrent cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-07-07 21:39:54 -04:00
parent 985cda6c7b
commit 6b38c7a04c
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/llama-memory-recurrent.cpp
View File

@@ -377,14 +377,18 @@ llama_memory_context_ptr llama_memory_recurrent::init_batch(llama_batch_allocr &
ubatch = balloc.split_equal(n_ubatch, false);
}
if (balloc.get_n_used() < balloc.get_n_tokens()) {
// failed to find a suitable split
if (ubatch.n_tokens == 0) {
break;
}
ubatches.push_back(std::move(ubatch)); // NOLINT
}
if (balloc.get_n_used() < balloc.get_n_tokens()) {
// failed to find a suitable split
break;
}
if (!prepare(ubatches)) {
break;
}