GeneralBots/gbserver
2
0
Fork 0
Code Issues 7 Pull requests Projects Releases Packages Wiki Activity Actions

- New settings for llama.cpp.
Some checks are pending
GBCI / build (push) Waiting to run
Details

Browse source
This commit is contained in:
Rodrigo Rodriguez (Pragmatismo) 2025-09-12 09:05:53 -03:00
parent 8936d0ce58
commit b682eead39
1 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
src/services/llm_local.rs
View file

@ -189,9 +189,11 @@ async fn start_llm_server(
std::env::set_var("OMP_PLACES", "cores"); std::env::set_var("OMP_PLACES", "cores");
std::env::set_var("OMP_PROC_BIND", "close"); std::env::set_var("OMP_PROC_BIND", "close");
// "cd {} && numactl --interleave=all ./llama-server -m {} --host 0.0.0.0 --port {} --threads 20 --threads-batch 40 --temp 0.7 --parallel 1 --repeat-penalty 1.1 --ctx-size 8192 --batch-size 8192 -n 4096 --mlock --no-mmap --flash-attn --no-kv-offload --no-mmap &",
let mut cmd = tokio::process::Command::new("sh"); let mut cmd = tokio::process::Command::new("sh");
cmd.arg("-c").arg(format!( cmd.arg("-c").arg(format!(
"cd {} && numactl --interleave=all ./llama-server -m {} --host 0.0.0.0 --port {} --threads 20 --threads-batch 40 --temp 0.7 --parallel 1 --repeat-penalty 1.1 --ctx-size 8192 --batch-size 8192 -n 4096 --mlock --no-mmap --flash-attn --no-kv-offload --no-mmap &", "cd {} && ./llama-server -m {} --host 0.0.0.0 --port {} --n-gpu-layers 99 --mlock --no-mmap --threads 20 --threads-batch 40 &",
llama_cpp_path, model_path, port llama_cpp_path, model_path, port
)); ));