Instructions to use yuhuili/EAGLE-LLaMA3-Instruct-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuhuili/EAGLE-LLaMA3-Instruct-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yuhuili/EAGLE-LLaMA3-Instruct-8B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yuhuili/EAGLE-LLaMA3-Instruct-8B")
model = AutoModelForCausalLM.from_pretrained("yuhuili/EAGLE-LLaMA3-Instruct-8B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yuhuili/EAGLE-LLaMA3-Instruct-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuhuili/EAGLE-LLaMA3-Instruct-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuhuili/EAGLE-LLaMA3-Instruct-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yuhuili/EAGLE-LLaMA3-Instruct-8B

SGLang

How to use yuhuili/EAGLE-LLaMA3-Instruct-8B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yuhuili/EAGLE-LLaMA3-Instruct-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuhuili/EAGLE-LLaMA3-Instruct-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yuhuili/EAGLE-LLaMA3-Instruct-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuhuili/EAGLE-LLaMA3-Instruct-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yuhuili/EAGLE-LLaMA3-Instruct-8B with Docker Model Runner:
```
docker model run hf.co/yuhuili/EAGLE-LLaMA3-Instruct-8B
```

Add model card for EAGLE-3

by nielsr HF Staff - opened Mar 10, 2025

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

+11

-0

Files changed (1) hide show

README.md +11 -0

README.md ADDED Viewed

	@@ -0,0 +1,11 @@

+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+---
+This repository contains the weights for the model described in [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://huggingface.co/papers/2503.01840).
+EAGLE-3 is the successor to EAGLE and EAGLE-2, and improves upon these using a novel multi-layer feature fusion method.
+Code: https://github.com/SafeAILab/EAGLE