Instructions to use inclusionAI/Ring-mini-linear-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ring-mini-linear-2.0 with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ring-mini-linear-2.0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ring-mini-linear-2.0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ring-mini-linear-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ring-mini-linear-2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inclusionAI/Ring-mini-linear-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ring-mini-linear-2.0

SGLang

How to use inclusionAI/Ring-mini-linear-2.0 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 "inclusionAI/Ring-mini-linear-2.0" \
    --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": "inclusionAI/Ring-mini-linear-2.0",
		"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 "inclusionAI/Ring-mini-linear-2.0" \
        --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": "inclusionAI/Ring-mini-linear-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ring-mini-linear-2.0 with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ring-mini-linear-2.0
```

caizhi1 commited on Sep 26, 2025

Commit

63fcfbd

verified ·

1 Parent(s): 1b5976d

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ This model continues to employ a hybrid architecture that combines linear attent
 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/PHRg8ipzJtr0p6sojAa5T.png" width="1000">
     <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 1:</strong> Hybrid Linear Model Architecture</p>
   </div>
 </div>
@@ -36,12 +36,12 @@ To better demonstrate our model's reasoning capabilities, we compared it with th
 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/RcHlh5PriRuOLsErG8RjK.webp" width="1000">
     <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 2:</strong> Model Performance Comparison </p>
   </div>
 </div>
-## Linear Attention, Highly Sparse，High-Speed Generation
 Thanks to its hybrid attention mechanism and highly sparse MoE architecture, Ring-mini-linear-2.0 achieves near-linear time complexity and constant space complexity, resulting in outstanding inference efficiency. To fully demonstrate this advantage, we conducted a head-to-head comparison between our model and top-tier competitors of similar size or performance.
 The results are remarkable. In the prefill stage, Ring-mini-linear-2.0's performance is exceptional; when the context length exceeds 256k, its throughput is over 12 times higher than that of Qwen3-8B. Furthermore, in the high-concurrency decode stage, its capabilities are even more pronounced. For generation lengths exceeding 32k, its throughput easily surpasses 12 times that of Qwen3-8B.

 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/PHRg8ipzJtr0p6sojAa5T.png" width="800">
     <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 1:</strong> Hybrid Linear Model Architecture</p>
   </div>
 </div>
 <div style="display: flex; justify-content: center;">
   <div style="text-align: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/68d20104a6f8ea66da0cb447/RcHlh5PriRuOLsErG8RjK.webp" width="100%">
     <p style="margin-top: 8px; font-size: 14px;"><strong>Figure 2:</strong> Model Performance Comparison </p>
   </div>
 </div>
+## Linear Attention, Highly Sparse, High-Speed Generation
 Thanks to its hybrid attention mechanism and highly sparse MoE architecture, Ring-mini-linear-2.0 achieves near-linear time complexity and constant space complexity, resulting in outstanding inference efficiency. To fully demonstrate this advantage, we conducted a head-to-head comparison between our model and top-tier competitors of similar size or performance.
 The results are remarkable. In the prefill stage, Ring-mini-linear-2.0's performance is exceptional; when the context length exceeds 256k, its throughput is over 12 times higher than that of Qwen3-8B. Furthermore, in the high-concurrency decode stage, its capabilities are even more pronounced. For generation lengths exceeding 32k, its throughput easily surpasses 12 times that of Qwen3-8B.