Update requirements.txt

requirements.txt

@@ -1,7 +1,5 @@
 fastapi>=0.115.0
 uvicorn[standard]>=0.30.0
-onnxruntime>=1.18.0
-onnxruntime-openvino>=1.18.0
 transformers>=5.1.0
 huggingface_hub>=0.24.0
 pillow>=10.4.0
@@ -9,5 +7,6 @@ numpy>=1.26.0
 requests>=2.32.0
 python-multipart>=0.0.9
 pydantic>=2.8.0
-torch>=2.4.0
-torchvision>=0.19.0
+
+# NEW: The Python bindings for llama.cpp
+llama-cpp-python>=0.3.0