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

server: revert change on slot n_ctx

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-03-02 14:12:12 +01:00
parent 2495f7273a
commit af82fb4ad7
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

@ -421,7 +421,7 @@ struct llama_server_context
// create slots
all_slots_are_idle = true;
const int32_t n_ctx_slot = std::min(n_ctx / params.n_parallel, llama_n_ctx_train(model)); // FIXME @ggerganov @phymbert To be discussed
const int32_t n_ctx_slot = n_ctx / params.n_parallel;
LOG_INFO("initializing slots", {{"n_slots", params.n_parallel}});
for (int i = 0; i < params.n_parallel; i++)