launch_vllm.py

# (Removed for Hugging Face Spaces)
#!/usr/bin/env python3
"""
Launch vLLM OpenAI-compatible server for google/gemma-3n-E4B-it in venv.
"""
from dotenv import load_dotenv
load_dotenv()
import os
import subprocess
import sys

MODEL = "google/gemma-3n-E4B-it"
PORT = os.environ.get("VLLM_PORT", "8000")
HF_TOKEN = os.environ.get("HF_TOKEN")  # User must set this for gated models

if not HF_TOKEN:
    print("[ERROR] Please set the HF_TOKEN environment variable for model download.")
    sys.exit(1)

cmd = [
    sys.executable, "-m", "vllm.entrypoints.openai.api_server",
    "--model", MODEL,
    "--port", PORT,
    "--host", "0.0.0.0",
    "--token", HF_TOKEN
]

print(f"[INFO] Launching vLLM server for {MODEL} on port {PORT}...")
subprocess.run(cmd)
#!/usr/bin/env python3
"""
Launch vLLM OpenAI-compatible server for google/gemma-3n-E4B-it in venv.
"""
from dotenv import load_dotenv
load_dotenv()
import os
import subprocess
import sys

MODEL = "google/gemma-3n-E4B-it"
PORT = os.environ.get("VLLM_PORT", "8000")
HF_TOKEN = os.environ.get("HF_TOKEN")  # User must set this for gated models

if not HF_TOKEN:
    print("[ERROR] Please set the HF_TOKEN environment variable for model download.")
    sys.exit(1)

cmd = [
    sys.executable, "-m", "vllm.entrypoints.openai.api_server",
    "--model", MODEL,
    "--port", PORT,
    "--host", "0.0.0.0",
    "--token", HF_TOKEN
]

print(f"[INFO] Launching vLLM server for {MODEL} on port {PORT}...")
subprocess.run(cmd)