Instructions to use stepfun-ai/step3-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/step3-fp8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="stepfun-ai/step3-fp8", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("stepfun-ai/step3-fp8", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stepfun-ai/step3-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/step3-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/step3-fp8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/stepfun-ai/step3-fp8

SGLang

How to use stepfun-ai/step3-fp8 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 "stepfun-ai/step3-fp8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/step3-fp8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "stepfun-ai/step3-fp8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/step3-fp8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use stepfun-ai/step3-fp8 with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/step3-fp8
```

Rico commited on Jul 31, 2025

Commit

adcb82c

1 Parent(s): b197bac

[update] update github and collection address

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -12,7 +12,7 @@
 </div>
 <div align="center" style="line-height: 1;">
-  <a href="https://github.com/stepfun-ai/Step3" target="_blank"><img alt="Github" src="https://img.shields.io/badge/🤖Github-StepFun-ffc107?color=ffc107&logoColor=white"/></a>
   <a href="https://www.modelscope.cn/models/stepfun-ai/step3" target="_blank"><img alt="ModelScope" src="https://img.shields.io/badge/🤖ModelScope-StepFun-ffc107?color=7963eb&logoColor=white"/></a>
   <a href="https://x.com/StepFun_ai" target="_blank"><img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-StepFun-white?logo=x&logoColor=white"/></a>
 </div>
@@ -378,7 +378,7 @@ print(decoded)
 ### Inference with vLLM and SGLang
-Our model checkpoints are stored in bf16 and block-fp8 format, you can find it on [Huggingface](https://huggingface.co/stepfun-ai/step3).
 Currently, it is recommended to run Step3 on the following inference engines:

 </div>
 <div align="center" style="line-height: 1;">
+  <a href="https://github.com/stepfun-ai/Step3" target="_blank"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-StepFun-white?logo=github&logoColor=white"/></a>
   <a href="https://www.modelscope.cn/models/stepfun-ai/step3" target="_blank"><img alt="ModelScope" src="https://img.shields.io/badge/🤖ModelScope-StepFun-ffc107?color=7963eb&logoColor=white"/></a>
   <a href="https://x.com/StepFun_ai" target="_blank"><img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-StepFun-white?logo=x&logoColor=white"/></a>
 </div>
 ### Inference with vLLM and SGLang
+Our model checkpoints are stored in bf16 and block-fp8 format, you can find it on [Huggingface](https://huggingface.co/collections/stepfun-ai/step3-688a3d652dbb45d868f9d42d).
 Currently, it is recommended to run Step3 on the following inference engines: