Skip to content

server: improve speed of speculative decoding #1119

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
ikawrakow merged 2 commits into from
Jan 10, 2026
Merged

server: improve speed of speculative decoding #1119

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
be66c65
server: improve speed of speculative decoding
Jan 7, 2026
e448b5c
Fix n_batch_size not set to context size for draft model
Jan 8, 2026
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
1 change: 1 addition & 0 deletions common/common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3556,6 +3556,7 @@ void llama_batch_add(
llama_pos pos,
const std::vector<llama_seq_id> & seq_ids,
bool logits) {
GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded");
batch.token [batch.n_tokens] = id;
batch.pos [batch.n_tokens] = pos;
batch.n_seq_id[batch.n_tokens] = seq_ids.size();
Expand Down
2 changes: 1 addition & 1 deletion examples/server/server-common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -484,7 +484,7 @@ bool server_sent_event(httplib::DataSink& sink, const json& data) {
data.dump(-1, ' ', false, json::error_handler_t::replace) +
"\n\n"; // required by RFC 8895 - A message is terminated by a blank line (two line terminators in a row).

LOG_VERBOSE("data stream, to_send: %s", str.c_str());
//LOG_VERBOSE("data stream, to_send: %s", str.c_str());

return sink.write(str.c_str(), str.size());
}
Expand Down
4 changes: 4 additions & 0 deletions examples/server/server-common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,6 +336,10 @@ struct server_tokens {

llama_pos pos_next() const;

int n_tokens() const {
return tokens.size();
}

// for debugging
std::string str() const;

Expand Down
Loading