Skip to content

server : enable multi-modal prompt caching #19877

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

Merged
ggerganov merged 1 commit into from
Feb 25, 2026
+1 −5
Merged

server : enable multi-modal prompt caching #19877

Show file tree
Hide file tree
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: 0 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 @@ -995,9 +995,6 @@ struct server_context_impl {
// don't update the cache if the slot's context is empty
update_cache = update_cache && tokens.size() > 0;

// TODO: mtmd does not support prompt cache
update_cache = update_cache && (ret->mctx == nullptr);

if (update_cache) {
SRV_WRN("%s", "updating prompt cache\n");

Expand Down
3 changes: 1 addition & 2 deletions tools/server/server-task.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1900,10 +1900,9 @@ server_prompt * server_prompt_cache::alloc(const server_prompt & prompt, size_t
return nullptr;
}

// TODO: for some reason we can't copy server_tokens, so we have to do this workaround
auto & cur = states.emplace_back();
cur = {
/*.tokens =*/ server_tokens(prompt.tokens.get_text_tokens(), false),
/*.tokens =*/ prompt.tokens.clone(),
/*.data =*/ std::move(state_data),
/*.checkpoints =*/ prompt.checkpoints,
};
Expand Down
Loading