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

-Lamma.cpp hardcoded config tests.
Some checks are pending
GBCI / build (push) Waiting to run
Details

Browse source
This commit is contained in:
Rodrigo Rodriguez (Pragmatismo) 2025-09-11 16:15:06 -03:00
parent dabc8171e0
commit 8936d0ce58
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/services/llm_local.rs
View file

@ -191,7 +191,7 @@ async fn start_llm_server(
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 10000 --batch-size 10000 -n 4096 --mlock --no-mmap --prompt-cache-all --flash-attn --no-kv-offload --tensor-split 100 --no-mmap &", "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 &",
llama_cpp_path, model_path, port llama_cpp_path, model_path, port
)); ));