Skip to content

server: ensure prompt caching for SWA models #21749

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
shipped-it wants to merge 1 commit into
base: master
Choose a base branch
from
+2 −2
Open

server: ensure prompt caching for SWA models #21749

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
4 changes: 2 additions & 2 deletions tools/server/server-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2344,7 +2344,7 @@ struct server_context_impl {
const auto n_swa = std::max(0, llama_model_n_swa(model));

// the largest pos_min required for a checkpoint to be useful
const auto pos_min_thold = std::max(0, pos_next - n_swa);
const auto pos_min_thold = params_base.swa_full ? 0 : std::max(0, pos_next - n_swa);

if (n_past > 0 && n_past < slot.prompt.n_tokens()) {
const auto pos_min = llama_memory_seq_pos_min(llama_get_memory(ctx), slot.id);
Expand Down Expand Up @@ -2396,7 +2396,7 @@ struct server_context_impl {
SLT_WRN(slot, "%s\n", st1.str().c_str());
}

if (pos_min >= pos_min_thold) {
if (pos_min >= pos_min_thold && !params_base.swa_full) {
SLT_WRN(slot, "n_past = %d, slot.prompt.tokens.size() = %d, seq_id = %d, pos_min = %d, n_swa = %d\n", n_past, (int) slot.prompt.tokens.size(), slot.id, pos_min, n_swa);

// search for a context checkpoint
Expand Down