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

ci: server: tests python env on github container ubuntu latest / fix n_predict (#6935)

Browse source 
* ci: server: fix python env

* ci: server: fix server tests after #6638

* ci: server: fix windows is not building PR branch
This commit is contained in:
Pierrick Hymbert 2024-04-27 17:50:48 +02:00 • committed by GitHub
parent 928e0b7013
commit b7368332e2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 15 additions and 18 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", {