Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-11 21:10:24 +01:00
Code Issues Packages Projects Releases Wiki Activity

server : fix typo in comment

Browse Source
This commit is contained in:
Francis Couture-Harpin 2024-08-13 22:12:26 -04:00
parent af2f84c964
commit 93ec58b932
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -754,7 +754,7 @@ struct server_context {
default_generation_settings_for_props = get_formated_generation(slots.front());
default_generation_settings_for_props["seed"] = -1;
// the update_slots() logic will always submit a maximum of n_batch or n_parralel tokens
// the update_slots() logic will always submit a maximum of n_batch or n_parallel tokens
// note that n_batch can be > n_ctx (e.g. for non-causal attention models such as BERT where the KV cache is not used)
{
const int32_t n_batch = llama_n_batch(ctx);