sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-03-17 16:44:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix ctx checkpoint restore logic (#19924)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-02-26 18:20:16 +02:00
committed by GitHub
parent 99bd67c9b2
commit 01cd448b8c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server-context.cpp
View File

@@ -2363,7 +2363,7 @@ private:
//printf("[DEBUG] `do_reset` was set to `true` after failing to restore a checkpoint");
} else {
pos_next = std::min(pos_next, std::max(it->pos_min + 1, it->pos_max));
n_past = slot.prompt.tokens.size_up_to_pos(pos_next);
n_past = std::min(slot.prompt.tokens.size_up_to_pos(pos_next), (size_t) it->n_tokens);
SLT_WRN(slot, "restored context checkpoint (pos_min = %d, pos_max = %d, n_tokens = %" PRId64 ", size = %.3f MiB)\n", it->pos_min, it->pos_max, it->n_tokens, (float) checkpoint_size / 1024 / 1024);
}
}