Instructions to use openbmb/MiniCPM-SALA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-SALA with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/MiniCPM-SALA", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM-SALA", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM-SALA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/openbmb/MiniCPM-SALA

SGLang

How to use openbmb/MiniCPM-SALA 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 "openbmb/MiniCPM-SALA" \
    --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": "openbmb/MiniCPM-SALA",
		"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 "openbmb/MiniCPM-SALA" \
        --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": "openbmb/MiniCPM-SALA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM-SALA with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-SALA
```

DennisHuang648 commited on Feb 11

Commit

42afc22

verified ·

1 Parent(s): 85b2dbe

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -19,6 +19,17 @@ library_name: transformers
 👋 Contact us in <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
 </p>
 ## What's New
 - [2026.02.11] **MiniCPM-SALA** is released! This is the first large-scale hybrid model effectively integrating sparse and linear attention for million-token context modeling. You can find technical report [here](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf).🔥🔥🔥

 👋 Contact us in <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
 </p>
+> [!NOTE]
+> ### 🏆 2026 Sparse Operator Acceleration & Race (SOAR) is Now Live!
+>
+> **"The MiniCPM-SALA architecture is just the beginning. Realizing its full potential requires deep system-level synergy and cross-layer compilation optimization."**
+>
+> In collaboration with **SGLang** and **NVIDIA**, OpenBMB invites global geeks to push the boundaries of 9B-scale, 1M-token inference on **NVIDIA 6000D**.
+>
+> 💰 **Prize Pool: >$100,000 USD** (🥇 Top Prize: **$89,000**) | 🚀 **Challenge:** Single & Multi-batch Optimization
+>
+> 👉 **[Click Here to Join the Race @ soar.openbmb.cn](https://soar.openbmb.cn/)**
 ## What's New
 - [2026.02.11] **MiniCPM-SALA** is released! This is the first large-scale hybrid model effectively integrating sparse and linear attention for million-token context modeling. You can find technical report [here](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf).🔥🔥🔥