Instructions to use openbmb/NOSA-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/NOSA-1B with Transformers:

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

pipe = pipeline("text-generation", model="openbmb/NOSA-1B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openbmb/NOSA-1B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("openbmb/NOSA-1B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openbmb/NOSA-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/NOSA-1B"
# 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/NOSA-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/NOSA-1B

SGLang

How to use openbmb/NOSA-1B 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/NOSA-1B" \
    --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/NOSA-1B",
		"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/NOSA-1B" \
        --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/NOSA-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/NOSA-1B with Docker Model Runner:
```
docker model run hf.co/openbmb/NOSA-1B
```

NOSA: Native and Offloadable Sparse Attention

Boost Decoding Efficiency via High-Locality Offloading

Overview

NOSA is a trainable sparse attention mechanism designed for KV-cache offloading with an explicit locality constraint, paired with an inference system (NOSI) to realize its efficiency. It improves long-context/long-generation quality over prior offloading baselines while boosting decoding throughput by up to 5.04× vs FullAttn, 1.92× vs InfLLMv2, and 1.83× vs ShadowKV on 1B/3B/8B LLMs.

For more details, please refer to the paper: NOSA: Native and Offloadable Sparse Attention.

Models

We train 1B, 3B, and 8B models FullAttn, InfLLMv2, DMA, and NOSA, resulting in a total of 12 models. The following models have been released on Hugging Face.

Model	Link
NOSA-1B	NOSA-1B
NOSA-3B	NOSA-3B
NOSA-8B	NOSA-8B

Please reach out to us if additional baseline models (FullAttn, InfLLMv2, or DMA) are needed. You may open an issue or contact us directly via email (our email addresses are provided in the paper).

Citation

@article{huang2025nosa,
  title={NOSA: Native and Offloadable Sparse Attention},
  author={Huang, Yuxiang and Wang, Pengjie and Han, Jicheng and Zhao, Weilin and Su, Zhou and Sun, Ao and Lyu, Hongya and Zhao, Hengyu and Wang, Yudong and Xiao, Chaojun and Han, Xu and Liu, Zhiyuan},
  journal={arXiv preprint arXiv:2510.13602},
  year={2025}
}

Downloads last month: 1,589

Dataset used to train openbmb/NOSA-1B

Collection including openbmb/NOSA-1B

NOSA

Collection

NOSA: Native and Offloadable Sparse Attention • 3 items • Updated 3 days ago • 3

Paper for openbmb/NOSA-1B

NOSA: Native and Offloadable Sparse Attention

Paper • 2510.13602 • Published Oct 15, 2025 • 7