CoolFace
Modelpublic

lkevincc0/Step-3.5-Flash-REAP-128B-A11B

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face
10likes74downloads
Model Card

Step-3.5-128B-A11B | Technical Specifications

AttributeDetail
Base ModelStep-3.5-Flash
ArchitectureSparse Mixture-of-Experts (SMoE)
Model TypeCausal Language Model
Total Parameters128B
Active Parameters11B (per token)
Compression Ratio40% (Expert Pruning)
Pruning StrategyPruning observation (REAP)
Calibration Setlkevincc0/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

bash
# 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
bash
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
bash
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

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"

2. Launch the server

  • —For BF16 model
bash
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
bash
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

Reference