root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-14 04:24:30 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

revert usage of GGML_ASSERT

Browse Source
This commit is contained in:
Xuan Son Nguyen 2024-09-23 15:20:29 +02:00
parent 8941264d7e
commit 770462aace
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

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