Instructions to use internlm/Intern-S2-Preview-397B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/Intern-S2-Preview-397B with Transformers:

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

pipe = pipeline("image-text-to-text", model="internlm/Intern-S2-Preview-397B", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("internlm/Intern-S2-Preview-397B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/Intern-S2-Preview-397B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/Intern-S2-Preview-397B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/Intern-S2-Preview-397B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/Intern-S2-Preview-397B

SGLang

How to use internlm/Intern-S2-Preview-397B 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 "internlm/Intern-S2-Preview-397B" \
    --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": "internlm/Intern-S2-Preview-397B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "internlm/Intern-S2-Preview-397B" \
        --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": "internlm/Intern-S2-Preview-397B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use internlm/Intern-S2-Preview-397B with Docker Model Runner:
```
docker model run hf.co/internlm/Intern-S2-Preview-397B
```

Intern-S2-Preview-397B / deployment_guide.md

haijunlv

Upload folder using huggingface_hub

dfd4935 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

4.09 kB

Intern-S2-Preview-397B Deployment Guide

We recommend deploying the Intern-S2-Preview-397B model on H100 (x8) or H200 (x8) nodes. The next section provides deployment examples for the configurations listed below:

Basic serving without MTP
MTP speculative decoding
Long-context inference with YaRN RoPE configuration

LMDeploy (>=0.14.0)

Basic Serving Without MTP

# proxy server
lmdeploy serve proxy --server-name ${proxy_server_ip} --server-port ${proxy_server_port} 

# api_server
lmdeploy serve api_server \
    internlm/Intern-S2-Preview-397B \
    --trust-remote-code \
    --backend pytorch \
    --dp 4 \
    --ep 8 \
    --enable-prefix-caching \
    --proxy-url http://${proxy_server_ip}:${proxy_server_port} \
    --reasoning-parser default \
    --tool-call-parser interns2-preview

Serving With MTP

lmdeploy serve api_server \
    internlm/Intern-S2-Preview-397B \
    --trust-remote-code \
    --backend pytorch \
    --dp 4 \
    --ep 8 \
    --enable-prefix-caching \
    --proxy-url http://${proxy_server_ip}:${proxy_server_port} \
    --reasoning-parser default \
    --tool-call-parser interns2-preview \
    --speculative-algorithm qwen3_5_mtp \
    --speculative-num-draft-tokens 4 \
    --max-batch-size 256

Long-Context Serving

For long-context inference, configure both --session-len and YaRN RoPE parameters. The following example uses a 512k context length:

lmdeploy serve api_server \
    internlm/Intern-S2-Preview-397B \
    --trust-remote-code \
    --backend pytorch \
    --dp 4 \
    --ep 8 \
    --enable-prefix-caching \
    --reasoning-parser default \
    --tool-call-parser interns2-preview \
    --session-len 512000 \
    --max-batch-size 64 \
    --hf-overrides '{"text_config": {"rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 4.0, "original_max_position_embeddings": 262144}}}'

vLLM (>=v0.22.1)

Basic Serving Without MTP

export VLLM_DEEP_GEMM_WARMUP=skip
export VLLM_USE_DEEP_GEMM=0
export VLLM_FLASHINFER_MOE_BACKEND=latency

vllm serve internlm/Intern-S2-Preview-397B \
  --trust-remote-code \
  --tensor-parallel-size 8 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --reasoning-parser qwen3 \
  --mm-encoder-tp-mode data

Serving With MTP

export VLLM_DEEP_GEMM_WARMUP=skip
export VLLM_USE_DEEP_GEMM=0
export VLLM_FLASHINFER_MOE_BACKEND=latency

vllm serve internlm/Intern-S2-Preview-397B \
  --trust-remote-code \
  --tensor-parallel-size 8 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --mm-encoder-tp-mode data \
  --reasoning-parser qwen3 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'

Long-Context Serving

VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve internlm/Intern-S2-Preview-397B \
  --tensor-parallel-size 8 \
  --max-model-len 1010000 \
  --reasoning-parser qwen3 \
  --hf-overrides '{"text_config": {"rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 4.0, "original_max_position_embeddings": 262144}}}'

SGLang (>=v0.5.13)

Basic Serving Without MTP

python3 -m sglang.launch_server \
    --model-path internlm/Intern-S2-Preview-397B \
    --trust-remote-code \
    --tp-size 8 \
    --mem-fraction-static 0.8 \
    --enable-flashinfer-allreduce-fusion \
    --reasoning-parser qwen3 \
    --tool-call-parser qwen3_coder

Serving With MTP

SGLANG_ENABLE_SPEC_V2=1 \
python3 -m sglang.launch_server \
  --model-path internLM/Intern-S2-Preview-397B \
  --trust-remote-code \
  --tp-size 8 \
  --reasoning-parser qwen3 \
  --tool-call-parser qwen3_coder \
  --mem-fraction-static 0.8 \
  --mamba-scheduler-strategy extra_buffer \
  --enable-flashinfer-allreduce-fusion \
  --speculative-algo 'NEXTN' \
  --speculative-eagle-topk 1 \
  --speculative-num-steps 3 \
  --speculative-num-draft-tokens 4