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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stepfun-ai/Step-3.5-Flash-FP8", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

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 13

Commit

1056dee

verified ·

1 Parent(s): 2c335f3

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -80,6 +80,10 @@ Performance of Step 3.5 Flash measured across **Reasoning**, **Coding**, and **A
 3. **BrowseComp (with Context Manager)**: When the effective context length exceeds a predefined threshold, the agent resets the context and restarts the agent loop. By contrast, Kimi K2.5 and DeepSeek-V3.2 used a "discard-all" strategy.
 4. **Decoding Cost**: Estimates are based on a methodology similar to, but more accurate than, the approach described arxiv.org/abs/2507.19427
 ## 4. Architecture Details
 Step 3.5 Flash is built on a **Sparse Mixture-of-Experts (MoE)** transformer architecture, optimized for high throughput and low VRAM usage during inference.

 3. **BrowseComp (with Context Manager)**: When the effective context length exceeds a predefined threshold, the agent resets the context and restarts the agent loop. By contrast, Kimi K2.5 and DeepSeek-V3.2 used a "discard-all" strategy.
 4. **Decoding Cost**: Estimates are based on a methodology similar to, but more accurate than, the approach described arxiv.org/abs/2507.19427
+### Recommended Inference Parameters
+1. For general chat domain, we suggest: `temperature=0.6, top_p=0.95`
+2. For reasoning / agent scenario, we recommend: `temperature=1.0, top_p=0.95`.
 ## 4. Architecture Details
 Step 3.5 Flash is built on a **Sparse Mixture-of-Experts (MoE)** transformer architecture, optimized for high throughput and low VRAM usage during inference.