Skip to content

hybrid recurrent memory cache fix (by mfielding92) #63

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

Open
vlisivka wants to merge 1 commit into
base: v0.3.2
Choose a base branch
from
+11 −3
Open

hybrid recurrent memory cache fix (by mfielding92) #63

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
14 changes: 11 additions & 3 deletions tools/server/server-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5527,7 +5527,7 @@ struct server_context_impl {
SLT_WRN(slot, "%s\n", st1.str().c_str());
}

if (pos_min >= pos_min_thold) {
if (n_swa > 0 && pos_min >= pos_min_thold) {
// search for a context checkpoint
const auto it = std::find_if(
slot.prompt.checkpoints.rbegin(),
Expand Down Expand Up @@ -5660,9 +5660,17 @@ struct server_context_impl {

SLT_TRC(slot, "cached n_tokens = %d, memory_seq_rm [%d, end)\n", slot.prompt.n_tokens(), p0);

common_context_seq_rm(ctx_tgt, slot.id, p0, -1);
if (!llama_memory_seq_rm(llama_get_memory(ctx_tgt), slot.id, p0, -1)) {
SLT_WRN(slot, "partial seq_rm at p0=%d failed (recurrent backend cannot roll into cache); clearing slot and re-evaluating from scratch\n", p0);
slot.n_prompt_tokens_cache = 0;
slot.prompt.tokens.keep_first(0);
common_context_seq_rm(ctx_tgt, slot.id, 0, -1);
}

if (ctx_dft) {
common_context_seq_rm(ctx_dft.get(), slot.id, p0, -1);
if (!llama_memory_seq_rm(llama_get_memory(ctx_dft.get()), slot.id, p0, -1)) {
common_context_seq_rm(ctx_dft.get(), slot.id, 0, -1);
}
}

// If using an alora, there may be uncached tokens that come
Expand Down