From 7202f81985ed8e1cb258d0a2138062c84500d52e Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Sat, 14 Mar 2026 08:28:31 +0000
Subject: [PATCH] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 studio/backend/core/inference/llama_cpp.py | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py
index 063a656ecb..e652d92ca2 100644
--- a/studio/backend/core/inference/llama_cpp.py
+++ b/studio/backend/core/inference/llama_cpp.py
@@ -344,13 +344,20 @@ class LlamaCppBackend:
 
             cmd = [
                 binary,
-                "-m", model_path,
-                "--port", str(self._port),
-                "-c", str(n_ctx),
-                "-ngl", str(n_gpu_layers),
-                "--parallel", "1",       # Single-user studio, saves VRAM
-                "--flash-attn", "on",    # Force flash attention for speed
-                "--fit", "on",           # Auto-fit to available device memory
+                "-m",
+                model_path,
+                "--port",
+                str(self._port),
+                "-c",
+                str(n_ctx),
+                "-ngl",
+                str(n_gpu_layers),
+                "--parallel",
+                "1",  # Single-user studio, saves VRAM
+                "--flash-attn",
+                "on",  # Force flash attention for speed
+                "--fit",
+                "on",  # Auto-fit to available device memory
             ]
 
             if n_threads is not None: