Instructions to use lkevincc0/Step-3.5-Flash-REAP-128B-A11B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lkevincc0/Step-3.5-Flash-REAP-128B-A11B with Transformers:

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

pipe = pipeline("text-generation", model="lkevincc0/Step-3.5-Flash-REAP-128B-A11B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("lkevincc0/Step-3.5-Flash-REAP-128B-A11B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lkevincc0/Step-3.5-Flash-REAP-128B-A11B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lkevincc0/Step-3.5-Flash-REAP-128B-A11B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lkevincc0/Step-3.5-Flash-REAP-128B-A11B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lkevincc0/Step-3.5-Flash-REAP-128B-A11B

SGLang

How to use lkevincc0/Step-3.5-Flash-REAP-128B-A11B 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 "lkevincc0/Step-3.5-Flash-REAP-128B-A11B" \
    --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": "lkevincc0/Step-3.5-Flash-REAP-128B-A11B",
		"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 "lkevincc0/Step-3.5-Flash-REAP-128B-A11B" \
        --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": "lkevincc0/Step-3.5-Flash-REAP-128B-A11B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lkevincc0/Step-3.5-Flash-REAP-128B-A11B with Docker Model Runner:
```
docker model run hf.co/lkevincc0/Step-3.5-Flash-REAP-128B-A11B
```

Step-3.5-128B-A11B | Technical Specifications

Attribute	Detail
Base Model	Step-3.5-Flash
Architecture	Sparse Mixture-of-Experts (SMoE)
Model Type	Causal Language Model
Total Parameters	128B
Active Parameters	11B (per token)
Compression Ratio	40% (Expert Pruning)
Pruning Strategy	Pruning observation (REAP)
Calibration Set	`lkevincc0/glm47-math-code-calibration-1024`

Local Deployment

Step 3.5 Flash is optimized for local inference and supports industry-standard backends including vLLM, SGLang, Hugging Face Transformers, and llama.cpp.

vLLM

We recommend using the latest nightly build of vLLM.

1. Install vLLM

# via Docker
docker pull vllm/vllm-openai:nightly

# or via pip (nightly wheels)
pip install -U vllm --pre \
  --index-url https://pypi.org/simple \
  --extra-index-url https://wheels.vllm.ai/nightly

2. Launch the server

Note: Full MTP3 support is not yet available in vLLM. We are actively working on a Pull Request to integrate this feature, which is expected to significantly enhance decoding performance.

For FP8 model

vllm serve <MODEL_PATH_OR_HF_ID> \
  --served-model-name step3p5-flash \
  --tensor-parallel-size 8 \
  --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 \
  --quantization fp8

For BF16 model

vllm serve <MODEL_PATH_OR_HF_ID> \
  --served-model-name step3p5-flash \
  --tensor-parallel-size 8 \
  --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

You can also refer to the Step-3.5-Flash recipe.

SGLang

1. Install SGLang

# 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"

2. Launch the server

For BF16 model

sglang serve --model-path <MODEL_PATH_OR_HF_ID> \
  --served-model-name step3p5-flash \
  --tp-size 8 \
  --tool-call-parser step3p5 \
  --reasoning-parser step3p5 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --enable-multi-layer-eagle \
  --host 0.0.0.0 \
  --port 8000

For FP8 model

sglang serve --model-path <MODEL_PATH_OR_HF_ID> \
  --served-model-name step3p5-flash \
  --tp-size 8 \
  --ep-size 8 \
  --tool-call-parser step3p5 \
  --reasoning-parser step3p5 \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 \
  --speculative-eagle-topk 1 \
  --speculative-num-draft-tokens 4 \
  --enable-multi-layer-eagle \
  --host 0.0.0.0 \
  --port 8000