wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

server-context: guarantee there is at least 1 token to decode (#23280)

Browse Source
This commit is contained in:
Pascal
2026-05-19 08:49:01 +02:00
committed by GitHub
parent 3c81c8deea
commit ccee426426
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+2 -2
View File
@@ -2589,9 +2589,9 @@ private:
llama_pos pos_next = slot.prompt.tokens.pos_next(n_past);
// the largest pos_min required for a checkpoint to be useful
const auto pos_min_thold = std::max(0, pos_next - n_swa);
const auto pos_min_thold = std::max(0, pos_next - n_swa - 1);
if (n_past > 0 && n_past < slot.prompt.n_tokens()) {
if (n_past > 0 && n_past <= slot.prompt.n_tokens()) {
const auto pos_min = llama_memory_seq_pos_min(llama_get_memory(ctx_tgt), slot.id);
if (pos_min == -1) {
SLT_ERR(slot, "n_past = %d, slot.prompt.tokens.size() = %d, seq_id = %d, pos_min = %d\n", n_past, (int) slot.prompt.tokens.size(), slot.id, pos_min);