スペキュレーティブデコーディング：ドラフトモデル、n-gram、MTP、そしてEAGLE

vllm serve meta-llama/Llama-3.1-70B-Instruct \
  --speculative-model ngram \
  --num-speculative-tokens 5 \
  --ngram-prompt-lookup-max 5 \
  --gpu-memory-utilization 0.90

vllm serve meta-llama/Llama-3.1-70B-Instruct \
  --speculative-model meta-llama/Llama-3.1-8B-Instruct \
  --num-speculative-tokens 5 \
  --gpu-memory-utilization 0.90 \
  --max-model-len 8192

./llama-server \
  --model models/llama-3.1-70b-q4_k_m.gguf \
  --draft ngram \
  --n-predict 128 \
  --lookup-cache-static \
  --port 8080

# Baseline (no speculation)
vllm serve meta-llama/Llama-3.1-70B-Instruct \
  --gpu-memory-utilization 0.90 \
  --max-model-len 8192 &

# Send a test request and note tok/s in the response headers
curl http://127.0.0.1:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.1-70B-Instruct",
    "messages": [{"role": "user", "content": "Write a Python class that implements a binary search tree with insert, delete, and search methods."}],
    "max_tokens": 512
  }'

python -m vllm.benchmarks.benchmark_serving \
  --model meta-llama/Llama-3.1-70B-Instruct \
  --num-prompts 10 \
  --request-rate 1