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
```

Cant run with tp 4

by darkstar3537 - opened Feb 3

Discussion

darkstar3537

Feb 3

•

edited Feb 3

Can't run with sglang PR docker container on 4 RTX 6000 Pro GPUs:

ValueError: The output_size of gate's and up's weight = 320 is not divisible by weight quantization block_n = 128.

Very disappointing for a model of this size for FP8

ordisbold

Feb 3

I already ran it with 4 x RTX 6000 Pro Blackwell.

You are wrong.

darkstar3537

Feb 3

I already ran it with 4 x RTX 6000 Pro Blackwell.

You are wrong.

"Note: The FP8 version of Step-3.5-Flash cannot use TP4. You can try DP4 instead"

Ok.

ordisbold

Feb 3

vllm serve stepfun-ai/Step-3.5-Flash-FP8
--served-model-name Step-3.5-Flash
--tensor-parallel-size 4
--enable-expert-parallel
--disable-cascade-attn
--reasoning-parser step3p5
--enable-auto-tool-choice
--tool-call-parser step3p5
--hf-overrides '{"num_nextn_predict_layers": 1}'
--speculative_config '{"method": "step3p5_mtp", "num_speculative_tokens": 1}'
--trust-remote-code

darkstar3537

Feb 3

Shrug, doesn't work for me w/nightly and docs say it's not supported

ordisbold

Feb 3

I just reinstalled again... because there's a bug in the tool call parser which I try to fix.

I used this to install vllm:

pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
Python 3.10

darkstar3537

Feb 3

•

edited Feb 3

Ok, I changed my ImagePullPolcy to Always and forced the fresh nightly pull. Works now

darkstar3537 changed discussion status to closed Feb 3

PremierSado

Feb 4

I just reinstalled again... because there's a bug in the tool call parser which I try to fix.

I used this to install vllm:

pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
Python 3.10

Where you successful in fixing it? Can you share the change?

ordisbold

Feb 4

No, because Qwen-Coder-Next came out and its performance was so good that I didn't care about Step-3.5-Flash anymore. 😅

jmnargi

Feb 4

I just reinstalled again... because there's a bug in the tool call parser which I try to fix.

I used this to install vllm:

pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
Python 3.10

Where you successful in fixing it? Can you share the change?

Enable expert parallel flag resolved this error for me

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment