kubectl describe resourcequota -n my-namespace
kubectl get resourcequota -o json | jq '.items[].status'

import asyncio
from collections import deque

class InferenceQueue:
    def __init__(self, max_concurrent: int = 10):
        self.semaphore = asyncio.Semaphore(max_concurrent)
        self.queue_depth = 0

    async def inference(self, client, prompt: str) -> str:
        self.queue_depth += 1
        async with self.semaphore:
            try:
                return await asyncio.to_thread(client.generate, prompt)
            finally:
                self.queue_depth -= 1