Llama-3.1-8B-Instruct-speculator.eagle3

Llama-3.1-8B-Instruct-speculator.eagle3

Model Overview

• Verifier: meta-llama/Llama-3.1-8B-Instruct
• Speculative Decoding Algorithm: EAGLE-3
• Model Architecture: Eagle3Speculator
• Release Date: 07/27/2025
• Version: 1.0
• Model Developers: RedHat

This is a speculator model designed for use with meta-llama/Llama-3.1-8B-Instruct, based on the EAGLE-3 speculative decoding algorithm. It was trained using the speculators library on a combination of the Aeala/ShareGPT_Vicuna_unfiltered and the HuggingFaceH4/ultrachat_200k datasets. This model should be used with the meta-llama/Llama-3.1-8B-Instruct chat template, specifically through the /chat/completions endpoint.

Use with vLLM

vllm serve meta-llama/Llama-3.1-8B-Instruct \
  -tp 1 \
  --speculative-config '{
    "model": "RedHatAI/Llama-3.1-8B-Instruct-speculator.eagle3",
    "num_speculative_tokens": 3,
    "method": "eagle3"
  }'

Evaluations

<h3>Use cases</h3> <table> <thead> <tr> <th>Use Case</th> <th>Dataset</th> <th>Number of Samples</th> </tr> </thead> <tbody> <tr> <td>Coding</td> <td>HumanEval</td> <td>168</td> </tr> <tr> <td>Math Reasoning</td> <td>gsm8k</td> <td>80</td> </tr> <tr> <td>Text Summarization</td> <td>CNN/Daily Mail</td> <td>80</td> </tr> </tbody> </table> <h3>Acceptance lengths</h3> <table> <thead> <tr> <th>Use Case</th> <th>k=1</th> <th>k=2</th> <th>k=3</th> <th>k=4</th> <th>k=5</th> <th>k=6</th> <th>k=7</th> </tr> </thead> <tbody> <tr> <td>Coding</td> <td>1.84</td> <td>2.50</td> <td>3.02</td> <td>3.36</td> <td>3.61</td> <td>3.83</td> <td>3.89</td> </tr> <tr> <td>Math Reasoning</td> <td>1.80</td> <td>2.40</td> <td>2.83</td> <td>3.13</td> <td>3.27</td> <td>3.40</td> <td>3.83</td> </tr> <tr> <td>Text Summarization</td> <td>1.70</td> <td>2.19</td> <td>2.50</td> <td>2.78</td> <td>2.77</td> <td>2.98</td> <td>2.99</td> </tr> </tbody> </table> <h3>Performance benchmarking (1xA100)</h3> <div style="display: flex; justify-content: center; gap: 20px;"> <figure style="text-align: center;"> <img src="assets/Llama-3.1-8B-Instruct-HumanEval.png" alt="Coding" width="100%"> </figure> <figure style="text-align: center;"> <img src="assets/Llama-3.1-8B-Instruct-math_reasoning.png" alt="Coding" width="100%"> </figure> <figure style="text-align: center;"> <img src="assets/Llama-3.1-8B-Instruct-summarization.png" alt="Coding" width="100%"> </figure> </div> <details> <summary>Details</summary> <strong>Configuration</strong>

• temperature: 0.6
• top_p: 0.9
• repetitions: 5
• time per experiment: 3min
• hardware: 1xA100
• vLLM version: 0.11.0
• GuideLLM version: 0.3.0

<strong>Command</strong>

GUIDELLM__PREFERRED_ROUTE="chat_completions" \
guidellm benchmark \
  --target "http://localhost:8000/v1" \
  --data "RedHatAI/speculator_benchmarks" \
  --data-args '{"data_files": "HumanEval.jsonl"}' \
  --rate-type sweep \
  --max-seconds 180 \
  --output-path "Llama-3.1-8B-Instruct-HumanEval.json" \
  --backend-args '{"extra_body": {"chat_completions": {"temperature":0.0}}}'

GuideLLM interface changed, so for compatibility with the latest version (v0.6.0), please use the following command:

GUIDELLM__PREFERRED_ROUTE="chat_completions" \
guidellm benchmark \
  --target "http://localhost:8000/v1" \
  --data "RedHatAI/speculator_benchmarks" \
  --data-args '{"data_files": "HumanEval.jsonl"}' \
  --profile sweep \
  --max-seconds 1800 \
  --output-path "my_output.json" \
  --backend-args '{"extras": {"body": {"temperature":0.6, "top_p":0.95, "top_k":20}}}'

</details>