sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests Actions 168 Packages Projects Releases Wiki Activity

server : speculative checkpointing (#19493)

Browse Source 
* server : speculative decoding using checkpoints

* server : fix draft check with checkpoints

* server : rename spec vars

* server : log levels

* server : refactored spec logic to speculative.cpp

* server : renamed spec checkpoints option

* server : fix spec checkpoints, logging

* speculative : checkpoints with draft model, logging

* server : n_tokens_cur and create_checkpoint in draft

* server : fix server_speculative_callback (slot.id)

* spec : fix ngram-map/begin idx_last_check

* spec : init ckpt (begin() wasn't called)

* chore: update webui build output

* server : restore sampler in spec checkpoint and clear mem

* cont : avoid --spec-use-checkpoints argument

* cont : remove server_prompt_checkpoint_with_size

* spec : rename (leave_draft_state)

* cont : clean-up

* cont : do not ignore partial drafts even if the are short

* cont : spec callback owned by session

* cont : simplify

* cont : avoid empty speculative session

* cont : simplify

* cont : simplify

* cont : enable mtmd speculative decoding

* cont : keep the spec sampler alive

* cont : simplify

* cont : fix nullptr deref + draft checkpoints

* cont : remove common_speculative_accept_response

* cont : remove callback

* cont : simplify

* cont : minor

* cont : simplify

* cont : fix accepted number

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Sascha Rogmann
2026-04-19 09:24:06 +02:00
committed by GitHub
parent 91fef95362
commit 455d8e4be8
10 changed files with 421 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-common.cpp
+13 -3
View File
@@ -391,15 +391,25 @@ void server_tokens::push_back(server_tokens & tokens) {
}
void server_tokens::insert(const llama_tokens & inp_tokens) {
GGML_ASSERT(!has_mtmd); // only allow this if mtmd is disabled
tokens.insert(tokens.end(), inp_tokens.begin(), inp_tokens.end());
}
const llama_tokens & server_tokens::get_text_tokens() const {
GGML_ASSERT(!has_mtmd); // only allow this if mtmd is disabled
const llama_tokens & server_tokens::get_tokens() const {
GGML_ASSERT(!has_mtmd);
return tokens;
}
llama_tokens server_tokens::get_text_tokens() const {
llama_tokens res;
res.reserve(tokens.size());
for (llama_token t : tokens) {
if (t != LLAMA_TOKEN_NULL) {
res.push_back(t);
}
}
return res;
}
void server_tokens::set_token(llama_pos pos, llama_token id) {
GGML_ASSERT(!has_mtmd); // only allow this if mtmd is disabled
tokens[pos] = id;