new server + thread settings

app.py

@@ -10,6 +10,7 @@ import requests
 import json
 import subprocess
 import gradio as gr
+import os
 
 today_date = datetime.today().strftime("%B %-d, %Y")  # noqa: DTZ002
 
@@ -38,7 +39,7 @@ gguf_path = hf_hub_download(
 
 # start llama-server
 subprocess.run(["chmod", "+x", "llama-server"])
-command = ["./llama-server", "-m", "google_gemma-3-1b-it-IQ4_NL.gguf", "-ngl", "0", "--temp", "0.0", "-c", "2048", "-t", "8", "--port", "8081"]
+command = ["./llama-server", "-m", "google_gemma-3-1b-it-IQ4_NL.gguf", "-ngl", "0", "--temp", "0.0", "-c", "2048", "-t", str(os.cpu_count()), "--port", "8081"]
 process = subprocess.Popen(command)
 print(f"Llama-server process started with PID {process.pid}")
 

llama-server

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ead85d6cb439c1f7abfcd987bd19e125471e0350e9035f2edbc2ec25af1014d
-size 6362744
+oid sha256:e8bb9756aaf882b0ee1d7da03347e58a9aa846ac4defde5d122633837c077749
+size 6358592