git lfs install

README.md

@@ -7,8 +7,6 @@ sdk: gradio
 sdk_version: 5.49.0
 app_file: app.py
 pinned: false
-hf_oauth: true
-hf_oauth_expiration_minutes: 480
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -6,7 +6,6 @@ import time
 import uuid
 import subprocess
 import requests
-
 from typing import List, Dict, Any, Iterator
 
 from dotenv import load_dotenv
@@ -26,8 +25,6 @@ from agentflow.models.utils import make_json_serializable_truncated
 from pathlib import Path
 from huggingface_hub import CommitScheduler
 
-import spaces
-
 # Get Huggingface token from environment variable
 HF_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
 
@@ -87,9 +84,7 @@ def start_vllm_service() -> bool:
             [
                 "vllm", "serve", VLLM_MODEL_NAME,
                 "--port", str(VLLM_PORT),
-                "--host", VLLM_HOST,
-                "--tensor-parallel-size", "1",
-                "--gpu-memory-utilization", "0.95"
+                "--host", VLLM_HOST
             ],
             text=True
         )
@@ -487,7 +482,7 @@ def parse_arguments():
     parser.add_argument("--openai_api_source", default="we_provided", choices=["we_provided", "user_provided"], help="Source of OpenAI API key.")
     return parser.parse_args()
 
-@spaces.GPU(duration=300)
+
 def solve_problem_gradio(user_query, max_steps=10, max_time=60, llm_model_engine=None, enabled_tools=None):
     """
     Wrapper function to connect the solver to Gradio.

requirements.txt

@@ -19,5 +19,4 @@ dashscope==1.24.2
 gradio
 # litellm==2.1.1
 # ollama==0.5.1
-# e2b_code_interpreter==2.0.0
-spaces
+# e2b_code_interpreter==2.0.0