emerging-techniques-speculative-decoding

Speculative Decoding: Accelerating LLM Inference

When to Use This Skill

Use Speculative Decoding when you need to:

• Speed up inference by 1.5-3.6× without quality loss
• Reduce latency for real-time applications (chatbots, code generation)
• Optimize throughput for high-volume serving
• Deploy efficiently on limited hardware
• Generate faster without changing model architecture

Key Techniques: Draft model speculative decoding, Medusa (multiple heads), Lookahead Decoding (Jacobi iteration)

Papers: Medusa (arXiv 2401.10774), Lookahead Decoding (ICML 2024), Speculative Decoding Survey (ACL 2024)

Installation

# Standard speculative decoding (transformers)
pip install transformers accelerate

# Medusa (multiple decoding heads)
git clone https://github.com/FasterDecoding/Medusa
cd Medusa
pip install -e .

# Lookahead Decoding
git clone https://github.com/hao-ai-lab/LookaheadDecoding
cd LookaheadDecoding
pip install -e .

# Optional: vLLM with speculative decoding
pip install vllm

Quick Start

Basic Speculative Decoding (Draft Model)

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load target model (large, slow)
target_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-70b-hf",
    device_map="auto",
    torch_dtype=torch.float16
)

# Load draft model (small, fast)
draft_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-7b-hf",
    device_map="auto",
    torch_dtype=torch.float16
)

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-hf")

# Generate with speculative decoding
prompt = "Explain quantum computing in simple terms:"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# Transformers 4.36+ supports assisted generation
outputs = target_model.generate(
    **inputs,
    assistant_model=draft_model,  # Enable speculative decoding
    max_new_tokens=256,
    do_sample=True,
    temperature=0.7,
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)