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)

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

Notebooks
Google Colab
Kaggle
Local Apps

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
```

Ring-mini-linear-2.0 fails on Kaggle due to missing dependency "fla"

by siyuan00 - opened Jan 8

Discussion

siyuan00

Jan 8

Description
I encountered an issue when trying to run Ring-mini-linear-2.0 on Kaggle.

When loading the model, the following error is raised:

ImportError: This modeling file requires the following packages that were not found in your environment: fla.
Run `pip install fla`

However, attempting to install the dependency fails:

pip install fla
ERROR: Could not find a version that satisfies the requirement fla (from versions: none)
ERROR: No matching distribution found for fla

This suggests that fla is not available as a public PyPI package, or is not accessible in Kaggle’s restricted environment.

Environment

Platform: Kaggle Notebook
Python version: (auto-provided by Kaggle)
Installation method: pip

Impact
This currently prevents Ring-mini-linear-2.0 from running on Kaggle out of the box.

Questions / Suggestions

Is fla an internal or private dependency?
Is there an alternative installation method (e.g., GitHub source, optional dependency, or fallback implementation)?
Would it be possible to vendor or make this dependency optional for broader platform compatibility (e.g., Kaggle, Colab)?

Thanks for the great work on the model. Any guidance would be appreciated.

bestfleer

inclusionAI org Jan 8

You need to run
pip install flash-linear-attention.

caizhi1

inclusionAI org Jan 8

pip install flash-linear-attention==0.3.2

from: https://huggingface.co/inclusionAI/Ring-mini-linear-2.0#requirements

siyuan00

Jan 9

Thanks. You may add this line in the kaggle code.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment