CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : include total "num_slots" in props endpoint (#5349)

Browse Source
This commit is contained in:
Justin Parker
2024-02-06 04:20:59 -05:00
committed by GitHub
parent 31e7903221
commit 8a79c591de
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/server/server.cpp
View File

@@ -432,6 +432,7 @@ struct llama_server_context
} }
default_generation_settings_for_props = get_formated_generation(slots.front()); default_generation_settings_for_props = get_formated_generation(slots.front());
default_generation_settings_for_props["num_slots"] = params.n_parallel;
default_generation_settings_for_props["seed"] = -1; default_generation_settings_for_props["seed"] = -1;
batch = llama_batch_init(n_ctx, 0, params.n_parallel); batch = llama_batch_init(n_ctx, 0, params.n_parallel);