From b334e49498e9491432358876ca57e456ec18ff5f Mon Sep 17 00:00:00 2001
From: Roland Tannous <rolandtannous@gravityq.ai>
Date: Sat, 14 Feb 2026 20:13:50 +0000
Subject: [PATCH] decouple reliance of backend on frontend for is_lora

---
 studio/backend/routes/inference.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/studio/backend/routes/inference.py b/studio/backend/routes/inference.py
index 9e57946565..b3ea1fa1be 100644
--- a/studio/backend/routes/inference.py
+++ b/studio/backend/routes/inference.py
@@ -69,10 +69,10 @@ async def load_model(request: LoadRequest):
         backend = get_inference_backend()
         
         # Create config using clean factory method
+        # is_lora is auto-detected from adapter_config.json on disk/HF
         config = ModelConfig.from_identifier(
             model_id=request.model_path,
             hf_token=request.hf_token,
-            is_lora=request.is_lora,
         )
         
         if not config: