Llama 4 MoE ve DeepSeek-R1: 24GB GPU Donanım Sınırları, vLLM PagedAttention ve think Filtreleme

# vLLM servisini 24GB GPU üzerinde başlatma
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-14B \
  --host 0.0.0.0 \
  --port 8000 \
  --dtype auto \
  --max-model-len 16384 \
  --gpu-memory-utilization 0.90 \
  --api-key "$VLLM_API_KEY"

# Test isteği
curl http://127.0.0.1:8000/v1/chat/completions \
  -H "Authorization: Bearer $VLLM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","messages":[{"role":"user","content":"Give a concise answer: 17*19?"}]}'

import re
from typing import Any
import httpx
from fastapi import FastAPI, Header, HTTPException
from pydantic import BaseModel

VLLM = "http://127.0.0.1:8000"
THINK_RE = re.compile(r"<think>.*?</think>\s*", re.DOTALL | re.IGNORECASE)
app = FastAPI()

class ChatRequest(BaseModel):
    model: str
    messages: list[dict[str, Any]]
    max_tokens: int | None = None

@app.post("/v1/chat/completions")
async def chat(req: ChatRequest, authorization: str | None = Header(default=None)) -> dict[str, Any]:
    if not authorization:
        raise HTTPException(401, "missing Authorization")
    payload = req.model_dump(exclude_none=True)
    payload["stream"] = False
    async with httpx.AsyncClient(timeout=180) as client:
        r = await client.post(
            f"{VLLM}/v1/chat/completions",
            json=payload,
            headers={"Authorization": authorization},
        )
        r.raise_for_status()
        data = r.json()
        for choice in data.get("choices", []):
            msg = choice.get("message") or {}
            if isinstance(msg.get("content"), str):
                msg["content"] = THINK_RE.sub("", msg["content"]).strip()
        return data