fix: target api.huggingface.co instead of api-inference to bypass DNS blocks

shared/inference_client.py

@@ -146,7 +146,7 @@ def generate(
     use_token = token or HF_TOKEN
 
     # Call direct HF serverless Inference API
-    url = f"https://api-inference.huggingface.co/models/{use_model}"
+    url = f"https://api.huggingface.co/models/{use_model}"
     headers = {}
     if use_token:
         headers["Authorization"] = f"Bearer {use_token}"