dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

Sync with upstream

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-05-16 21:51:59 +02:00
parent d2a5905500
commit b9cf7c31b9
1 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
backend/cpp/llama/grpc-server.cpp
View file

@ -2272,6 +2272,14 @@ struct server_context {
slot.has_next_token = true; slot.has_next_token = true;
} }
// if context shifting is disabled, make sure that we don't run out of context
if (!params_base.ctx_shift && slot.n_past + 1 >= slot.n_ctx) {
slot.stop = STOP_TYPE_LIMIT;
slot.has_next_token = false;
SLT_DBG(slot, "stopped due to running out of context, n_past = %d, n_ctx = %d\n", slot.n_past, slot.n_ctx);
}
// check the limits // check the limits
if (slot.n_decoded > 0 && slot.has_next_token && !slot.has_budget(params_base)) { if (slot.n_decoded > 0 && slot.has_next_token && !slot.has_budget(params_base)) {
slot.stop = STOP_TYPE_LIMIT; slot.stop = STOP_TYPE_LIMIT;