vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

small fix

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-09-23 14:26:00 +02:00
parent c2e7945bb4
commit 3a64932e1f
1 changed files with 2 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/server/server.cpp
View file

@ -1837,10 +1837,8 @@ struct server_context {
if (slot.ga_n == 1) { if (slot.ga_n == 1) {
if (slot.is_processing() && (int) system_tokens.size() + slot.n_past >= slot.n_ctx - 1) { if (slot.is_processing() && (int) system_tokens.size() + slot.n_past >= slot.n_ctx - 1) {
if (!params.ctx_shift) { if (!params.ctx_shift) {
// this check is redundant (for good) // we should never get here, because generation should already stopped in process_token()
// we should never get here, since n_predict is already limited GGML_ASSERT(false && "context shifting is disabled");
slot.release();
send_error(slot, "context shift is disabled", ERROR_TYPE_SERVER);
continue; continue;
} }