mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 34 Packages Projects Releases Wiki Activity

spec : disacard last drafted token with low prob (#22506)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-04-29 17:00:00 +03:00
committed by GitHub
parent b1d5f5b449
commit 683c5acb90
2 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/speculative.cpp
+6 -6
View File
@@ -467,7 +467,7 @@ struct common_speculative_state_draft : public common_speculative_state {
prompt_dft.push_back(id_last);
LOG_DBG("%s: draft prompt: %s\n", __func__, string_from(ctx_dft, prompt_dft).c_str());
//LOG_DBG("%s: draft prompt: %s\n", __func__, string_from(ctx_dft, prompt_dft).c_str());
int ret = llama_decode(ctx_dft, batch);
if (ret != 0 && ret != 1) {
@@ -495,14 +495,14 @@ struct common_speculative_state_draft : public common_speculative_state {
common_sampler_accept(smpl, id, true);
result.push_back(id);
if (sparams.n_max <= (int) result.size()) {
// only collect very high-confidence draft tokens
if (cur_p->data[0].p < sparams.p_min) {
break;
}
// only collect very high-confidence draft tokens
if (cur_p->data[0].p < sparams.p_min) {
result.push_back(id);
if (sparams.n_max <= (int) result.size()) {
break;
}