Speculative Decoding

Traditional:  y_t = f(x, y_1, ..., y_{t-1})  (sequential)
Jacobi:       y_t^{(k+1)} = f(x, y_1^{(k)}, ..., y_{t-1}^{(k)})  (parallel)

class LookaheadDecoding:
    def __init__(self, model, window_size=15, ngram_size=5):
        self.model = model
        self.W = window_size  # Lookahead window
        self.N = ngram_size   # N-gram size

    def generate_step(self, tokens):
        # Lookahead branch: Generate W × N candidates
        candidates = {}
        for w in range(1, self.W + 1):
            for n in range(1, self.N + 1):
                # Generate n-gram starting at position w
                ngram = self.generate_ngram(tokens, start=w, length=n)
                candidates[(w, n)] = ngram

        # Verification branch: Find matching n-grams
        verified = []
        for ngram in candidates.values():
            if ngram[0] == tokens[-1]:  # First token matches last input
                if self.verify(tokens, ngram):
                    verified.append(ngram)

        # Accept longest verified n-gram
        return max(verified, key=len) if verified else [self.model.generate_next(tokens)]

from medusa.model.medusa_model import MedusaModel
from medusa.model.kv_cache import initialize_past_key_values
import torch.nn as nn

# 1. Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "lmsys/vicuna-7b-v1.3",
    torch_dtype=torch.float16
)

# 2. Add Medusa heads
num_heads = 4
medusa_heads = nn.ModuleList([
    nn.Linear(base_model.config.hidden_size, base_model.config.vocab_size, bias=False)
    for _ in range(num_heads)
])

# 3. Training loop (freeze base model for Medusa-1)
for param in base_model.parameters():
    param.requires_grad = False  # Freeze base

optimizer = torch.optim.Adam(medusa_heads.parameters(), lr=1e-3)

for batch in dataloader:
    # Forward pass
    hidden_states = base_model(**batch, output_hidden_states=True).hidden_states[-1]

    # Predict future tokens with each head
    loss = 0
    for i, head in enumerate(medusa_heads):
        logits = head(hidden_states)
        # Target: tokens shifted by (i+1) positions
        target = batch['input_ids'][:, i+1:]
        loss += F.cross_entropy(logits[:, :-i-1], target)

    # Backward
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

# Use Medusa as draft model for speculative decoding
draft_medusa = MedusaModel.from_pretrained("medusa-vicuna-7b")
target_model = AutoModelForCausalLM.from_pretrained("vicuna-33b")

# Draft generates multiple candidates with Medusa
draft_tokens = draft_medusa.medusa_generate(prompt, max_new_tokens=5)

# Target verifies in single forward pass
outputs = target_model.generate(
    prompt,
    assistant_model=draft_medusa,  # Use Medusa as draft
    max_new_tokens=256
)

# Combines benefits: Medusa speed + large model quality

def select_draft_model(target_model_size, target):
    """Select optimal draft model for speculative decoding."""
    # Rule: Draft should be 5-10× smaller
    if target_model_size == "70B":
        return "7B"  # 10× smaller
    elif target_model_size == "33B":
        return "7B"  # 5× smaller
    elif target_model_size == "13B":
        return "1B"  # 13× smaller
    else:
        return None  # Target too small, use Medusa/Lookahead instead

# Example
draft = select_draft_model("70B", target_model)
# Returns "7B" → Use Llama-2-7b as draft for Llama-2-70b

# New deployment → Medusa (best overall speedup, no draft model)
if deploying_new_model:
    use_method = "Medusa"

# Existing deployment with small model available → Draft speculative
elif have_small_version_of_model:
    use_method = "Draft Model Speculative"

# Want zero training/setup → Lookahead
elif want_plug_and_play:
    use_method = "Lookahead Decoding"

# K = number of speculative tokens
K = 4  # Good default
K = 2  # Conservative (higher acceptance)
K = 8  # Aggressive (lower acceptance, but more when accepted)

# Rule: Larger K → more speedup IF draft model is good

# Posterior threshold (acceptance confidence)
posterior_threshold = 0.09  # Standard (from paper)
posterior_threshold = 0.05  # More conservative (slower, higher quality)
posterior_threshold = 0.15  # More aggressive (faster, may degrade quality)

# Tree depth (how many steps ahead)
medusa_choices = [[0], [0, 0], [0, 1], [0, 0, 0]]  # Depth 3 (standard)

# Window size W (lookahead distance)
# N-gram size N (context for generation)

# 7B model (more resources)
W, N = 15, 5

# 13B model (moderate)
W, N = 10, 5

# 33B+ model (limited resources)
W, N = 7, 5

# vLLM with speculative decoding
from vllm import LLM, SamplingParams

# Initialize with draft model
llm = LLM(
    model="meta-llama/Llama-2-70b-hf",
    speculative_model="meta-llama/Llama-2-7b-hf",  # Draft model
    num_speculative_tokens=5,
    use_v2_block_manager=True,
)

# Generate
prompts = ["Tell me about AI:", "Explain quantum physics:"]
sampling_params = SamplingParams(temperature=0.7, max_tokens=256)

outputs = llm.generate(prompts, sampling_params)
for output in outputs:
    print(output.outputs[0].text)