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

ci: server: fix server tests after #6638

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-04-26 21:43:29 +02:00
parent d3b1c4e953
commit ed979270d2
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -1208,7 +1208,7 @@ struct server_context {
}
auto n_ctx_train = llama_n_ctx_train(model);
if (slot.params.n_predict < 1 && slot.ga_n == 1
if (slot.params.n_predict < 1 && slot.n_predict < 1 && slot.ga_n == 1
&& slot.n_prompt_tokens + slot.n_decoded >= n_ctx_train) {
LOG_WARNING("n_predict is not set and self-context extend is disabled."
" Limiting generated tokens to n_ctx_train to avoid EOS-less generation infinite loop", {