PR: Fix grader inference routing by using Inference Providers (minimal code change)

app.py

@@ -9,7 +9,7 @@ import black
 # Initialize the inference client
 HF_TOKEN = os.getenv("HF_TOKEN")
 HF_API_URL = os.getenv("HF_API_URL", "Qwen/Qwen2.5-Coder-32B-Instruct")
-client = InferenceClient(model=HF_API_URL, token=HF_TOKEN)
+client = InferenceClient(model=HF_API_URL, provider="auto", token=HF_TOKEN)
 
 # Load questions from Hugging Face dataset
 EXAM_MAX_QUESTIONS = int(os.getenv("EXAM_MAX_QUESTIONS", 1))

requirements.txt

@@ -34,7 +34,7 @@ gradio-client==1.7.0
 h11==0.14.0
 httpcore==1.0.7
 httpx==0.28.1
-huggingface-hub==0.28.1
+huggingface-hub==1.4.1
 idna==3.10
 ipykernel==6.29.5
 ipython==8.32.0