Instructions to use stepfun-ai/Step-3.5-Flash-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/Step-3.5-Flash-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="stepfun-ai/Step-3.5-Flash-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stepfun-ai/Step-3.5-Flash-FP8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("stepfun-ai/Step-3.5-Flash-FP8", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stepfun-ai/Step-3.5-Flash-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/Step-3.5-Flash-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/Step-3.5-Flash-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stepfun-ai/Step-3.5-Flash-FP8

SGLang

How to use stepfun-ai/Step-3.5-Flash-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/Step-3.5-Flash-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/Step-3.5-Flash-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Step-3.5-Flash-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/Step-3.5-Flash-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stepfun-ai/Step-3.5-Flash-FP8 with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/Step-3.5-Flash-FP8
```

WinstonDeng commited on Feb 2

Commit

433124f

verified ·

1 Parent(s): d16e6d5

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -10,11 +10,12 @@ base_model:
 <div align="center" style="display: flex; justify-content: center; align-items: center;">
   <img src="stepfun.svg" width="25" style="margin-right: 10px;"/>
-  <h1 style="margin: 0; border-bottom: none;">Step-3.5-Flash</h1>
 </div>
 [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20HF-StepFun/STEP3p5-preview)](https://huggingface.co/stepfun-ai/Step-3.5-Flash-FP8)
 [![ModelScope](https://img.shields.io/badge/ModelScope-StepFun/STEP3p5-preview)](https://huggingface.co/stepfun-ai/step3p5_preview/tree/main)
 [![Paper](https://img.shields.io/badge/Paper-Arxiv-red)](https://huggingface.co/stepfun-ai/Step-3.5-Flash-FP8)
 [![License](https://img.shields.io/badge/License-Apache%202.0-green)]()
@@ -22,7 +23,7 @@ base_model:
 ## 1. Introduction
-**Step 3.5 Flash** is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
 ## 2. Key Capabilities
@@ -213,7 +214,7 @@ vllm serve <MODEL_PATH_OR_HF_ID> \
 1. Install SGLang.
 ```bash
 # via Docker
-docker pull lmsysorg/sglang:latest
 # or from source (pip)
 pip install "sglang[all] @ git+https://github.com/sgl-project/sglang.git"
 ```

 <div align="center" style="display: flex; justify-content: center; align-items: center;">
   <img src="stepfun.svg" width="25" style="margin-right: 10px;"/>
+  <h1 style="margin: 0; border-bottom: none;">Step 3.5 Flash</h1>
 </div>
 [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20HF-StepFun/STEP3p5-preview)](https://huggingface.co/stepfun-ai/Step-3.5-Flash-FP8)
 [![ModelScope](https://img.shields.io/badge/ModelScope-StepFun/STEP3p5-preview)](https://huggingface.co/stepfun-ai/step3p5_preview/tree/main)
+[![Webpage](https://img.shields.io/badge/Webpage-Blog-blue)](https://static.stepfun.com/blog/step-3.5-flash/)
 [![Paper](https://img.shields.io/badge/Paper-Arxiv-red)](https://huggingface.co/stepfun-ai/Step-3.5-Flash-FP8)
 [![License](https://img.shields.io/badge/License-Apache%202.0-green)]()
 ## 1. Introduction
+**Step 3.5 Flash** ([visit website](https://static.stepfun.com/blog/step-3.5-flash/)) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
 ## 2. Key Capabilities
 1. Install SGLang.
 ```bash
 # via Docker
+docker pull lmsysorg/sglang:dev-pr-18084
 # or from source (pip)
 pip install "sglang[all] @ git+https://github.com/sgl-project/sglang.git"
 ```