Instructions to use Inferact/MiniMax-M3-EAGLE3-GQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Inferact/MiniMax-M3-EAGLE3-GQA with Transformers:

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

pipe = pipeline("text-generation", model="Inferact/MiniMax-M3-EAGLE3-GQA")

# Load model directly
from transformers import AutoTokenizer, LlamaForCausalLMEagle3

tokenizer = AutoTokenizer.from_pretrained("Inferact/MiniMax-M3-EAGLE3-GQA")
model = LlamaForCausalLMEagle3.from_pretrained("Inferact/MiniMax-M3-EAGLE3-GQA")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Inferact/MiniMax-M3-EAGLE3-GQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Inferact/MiniMax-M3-EAGLE3-GQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inferact/MiniMax-M3-EAGLE3-GQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Inferact/MiniMax-M3-EAGLE3-GQA

SGLang

How to use Inferact/MiniMax-M3-EAGLE3-GQA 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 "Inferact/MiniMax-M3-EAGLE3-GQA" \
    --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": "Inferact/MiniMax-M3-EAGLE3-GQA",
		"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 "Inferact/MiniMax-M3-EAGLE3-GQA" \
        --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": "Inferact/MiniMax-M3-EAGLE3-GQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Inferact/MiniMax-M3-EAGLE3-GQA with Docker Model Runner:
```
docker model run hf.co/Inferact/MiniMax-M3-EAGLE3-GQA
```

MiniMax-M3-EAGLE3-GQA / README.md

ZixiQi

Add per-position accept rate to Performance table

9669248 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

1.75 kB

metadata

license: mit
library_name: transformers
base_model: MiniMaxAI/Minimax-M3-preview
pipeline_tag: text-generation
tags:
  - eagle3
  - speculative-decoding
  - draft-model
  - gqa
  - vllm
  - torchspec
  - minimax

Model Overview

Inferact/MiniMax-M3-EAGLE3-GQA is a grouped-query-attention (GQA) EAGLE3 draft model for accelerating inference of MiniMax-M3, served with vLLM and trained with TorchSpec.

It is retrained on the same datasets as the multi-head-attention version Inferact/MiniMax-M3-EAGLE3 — kimi-mtp, OpenCodeInstruct, SWE-bench, and SWE-bench-Pro — with the draft's attention changed from MHA to GQA (num_key_value_heads: 64 → 4) for inference efficiency (16× smaller draft KV cache) and compatibility with the target model.

The draft is a 1-layer dense Llama (LlamaForCausalLMEagle3) on MiniMax-M3's hidden_size=6144 / vocab_size=200064; at serve time it shares the target's embedding and LM head (EAGLE3). See config.json for the full architecture.

Performance

Mean accepted length and draft accept rate measured end-to-end against MiniMaxAI/MiniMax-M3-MXFP8 served with vLLM at tensor-parallel-size=4, num_speculative_tokens=3, greedy sampling (temperature=0, top_p=1.0), max-concurrency=16.

Dataset	n	Mean accepted length	Draft accept rate	Per-position accept rate (pos 1 / 2 / 3)
MT-Bench	64	2.668	55.62%	0.745 / 0.537 / 0.387
SPEED-Bench (qualitative)	64	2.561	52.04%	0.719 / 0.500 / 0.342