yuhuili

yuhuili/EAGLE3-LLaMA3.1-Instruct-8B

 EAGLE...

Model Documentation

EAGLE

benchmark

EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency) is a new baseline for fast decoding of Large Language Models (LLMs) with provable performance maintenance. This approach involves extrapolating the second-top-layer contextual feature vectors of LLMs, enabling a significant boost in generation efficiency.

EAGLE is:

certified by the third-party evaluation as the fastest speculative method so far.

achieving 2x speedup on gpt-fast.

3x faster than vanilla decoding (13B).

2x faster than Lookahead (13B).

1.6x faster than Medusa (13B).

provably maintaining the consistency with vanilla decoding in the distribution of generated texts.

trainable (within 1-2 days) and testable on 8x RTX 3090 GPUs. So even the GPU poor can afford it.

combinable with other parallelled techniques such as vLLM, DeepSpeed, Mamba, FlashAttention, quantization, and hardware optimization.

EAGLE-2 uses the confidence scores from the draft model to approximate acceptance rates, dynamically adjusting the draft tree structure, which further enhances performance.

EAGLE-2 is:

4x faster than vanilla decoding (13B).

1.4x faster than EAGLE-1 (13B).

EAGLE-3 removes the feature prediction constraint in EAGLE and simulates this process during training using training-time testing. Considering that top-layer features are limited to next-token prediction, EAGLE-3 replaces them with a fusion of low-, mid-, and high-level semantic features. EAGLE-3 further improves generation speed while ensuring lossless performance.

EAGLE-3 is:

5.6 faster than vanilla decoding (13B).

1.8x faster than EAGLE-1 (13B).

demogif

_Inference is conducted on 2x RTX 3090 GPUs at fp16 precision using the Vicuna 13B model._

[//]:

()

[//]:

()

[//]:

(Using EAGLE-2, the inference speed on 2 RTX 3060 GPUs can be faster than vanilla autoregressive decoding on an A100 GPU.)

Support

EAGLE has been merged in the following mainstream LLM serving frameworks (listed in alphabetical order).

AMD ROCm

AngelSlim

AWS NeuronX Distributed Core

CPM.cu

Intel® Extension for Transformers

Intel® LLM Library for PyTorch

MLC-LLM

NVIDIA NeMo Framework

NVIDIA TensorRT-LLM

NVIDIA TensorRT Model Optimizer

Reference

For technical details and full experimental results, please check the paper of EAGLE, the paper of EAGLE-2, and the paper of EAGLE-3.


@inproceedings{li2024eagle, 
	author = {Yuhui Li and Fangyun Wei and Chao Zhang and Hongyang Zhang}, 
	title = {{EAGLE}: Speculative Sampling Requires Rethinking Feature Uncertainty}, 
	booktitle = {International Conference on Machine Learning},
	year = {2024}
}
@inproceedings{li2024eagle2, 
	author = {Yuhui Li and Fangyun Wei and Chao Zhang and Hongyang Zhang}, 
	title = {{EAGLE-2}: Faster Inference of Language Models with Dynamic Draft Trees}, 
	booktitle = {Empirical Methods in Natural Language Processing},
	year = {2024}
}
@inproceedings{li2025eagle3,
    author = {Yuhui Li and Fangyun Wei and Chao Zhang and Hongyang Zhang},
    title = {{EAGLE-3}: Scaling up Inference Acceleration of Large Language Models via Training-Time Test}, 
    booktitle = {Annual Conference on Neural Information Processing Systems},
    year = {2025}
}

Files & Weights

Filename	Size	Action
pytorch_model.bin	0.79 GB