Skip to content

memory : return an error instead of aborting on multi-range on-device state save #28209

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

Draft
vahpetr wants to merge 1 commit into
base: master
Choose a base branch
from
+2 −1
Draft

memory : return an error instead of aborting on multi-range on-device state save #28209

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
3 changes: 2 additions & 1 deletion src/llama-memory-recurrent.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -822,7 +822,8 @@ void llama_memory_recurrent::state_write(llama_io_write_i & io, llama_seq_id seq
}

if ((flags & LLAMA_STATE_SEQ_FLAGS_ON_DEVICE) && cell_ranges.size() > 1) {
GGML_ABORT("cannot save/load multiple ranges of cells to/from device memory\n");
// throw instead of aborting: state_seq_get_size/get_data catch this and return 0
throw std::runtime_error("cannot save/load multiple ranges of cells to/from device memory");
}

// DEBUG CHECK: Sum of cell counts in ranges should equal the total cell count
Expand Down