happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

server : fix off-by-one in pos_min_thold

This commit is contained in:
Georgi Gerganov 2026-03-20 10:27:48 +02:00
parent 6051df2f2b
commit 92a70fef1a
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tools/server/server-context.cpp
View File

@ -2307,8 +2307,8 @@ private:
llama_pos pos_next = slot.prompt.tokens.pos_next(n_past);
// note: when n_swa == 0, the model does not use SWA, which is equivalent to a window of 1
const auto n_swa = std::max(1, llama_model_n_swa(model));
// note: when n_swa == 0, the model does not use SWA
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);
@ -2363,7 +2363,7 @@ private:
SLT_WRN(slot, "%s\n", st1.str().c_str());
}
if (pos_min > pos_min_thold) {
if (pos_min >= pos_min_thold) {
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