nebius / MLP-Speculator-Llama-3.1-8B-Instruct

Model Description

This is an MLP-Speculator draft model for Llama-3.1-8B-Instruct , trained from scratch using LK losses — training objectives that directly target acceptance rate rather than using KL divergence as a proxy.

Training Details

• Base model : meta-llama/Llama-3.1-8B-Instruct
• Draft architecture : MLP-Speculator
• Training data : Infinity-Instruct-0625 with Llama-3.1-8B generated responses
• Training objective : Hybrid LK loss with adaptive λ scheduling (η=3)
• Training : 10 epochs from random initialization
• Draft length : K = 6 speculative tokens

Performance

Average acceptance length (τ) measured across MT-bench, HumanEval, and GSM8K with K = 6:

Measured at temperature = 1 with K = 6

Usage with vLLM

from vllm import LLM, SamplingParams

llm = LLM(
    model="meta-llama/Llama-3.1-8B-Instruct",
    speculative_config={
        "method": "mlp_speculator",
        "model": "nebius/MLP-Speculator-Llama-3.1-8B-Instruct",
        "num_speculative_tokens": 6,
    },
)

sampling_params = SamplingParams(temperature=0.7)
outputs = llm.generate(["Explain speculative decoding in simple terms."], sampling_params)

Note : The current vLLM implementation samples draft tokens greedily regardless of temperature settings, which can underestimate acceptance rates at temperature > 0. A community fix is under development (see vllm-project/vllm#20459 ). The acceptance metrics reported above were measured with proper rejection sampling.

License

CC BY 4.0

This model was trained using outputs from meta-llama/Llama-3.1-8B-Instruct . Use of this model is additionally subject to the Llama 3.1 Community License Agreement .

Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

Citation

@misc{samarin2026lklosses,
  title     = {LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding},
  author    = {Alexander Samarin and Sergei Krutikov and Anton Shevtsov and Sergei Skvortsov and Filipp Fisin and Alexander Golubev},
  year      = {2026},
  eprint    = {2602.23881},
  archivePrefix = {arXiv},
  primaryClass  = {cs.LG},
  url       = {https://arxiv.org/abs/2602.23881}
}