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

Libraries

How to use inclusionAI/Ring-lite-linear-preview with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ring-lite-linear-preview", 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-lite-linear-preview", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ring-lite-linear-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ring-lite-linear-preview"
# 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-lite-linear-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ring-lite-linear-preview

SGLang

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

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

zhangdonghao commited on Apr 24, 2025

Commit

da05ced

verified ·

1 Parent(s): 506c39c

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ pipeline_tag: text-generation
 # Ring-lite-linear-preview
 <p align="center">
-    <img src="https://huggingface.co/inclusionAI/Ring-lite-distill-preview/resolve/main/ant-bailing.png" width="100"/>
 <p>
 <p align="center">
@@ -52,12 +52,12 @@ In terms of the evaluation of reasoning ability， Ring-lite-linear-preview achi
 To evaluate the generation throughput, we deploy Ring-lite-linear and the softmax-attention-based Ring-lite based on vLLM on a single NVIDIA A100 GPU. Specifically, the input sequence length is fixed to 1. The end-to-end (E2E) generation time required for generating output sequences of varying lengths is illustrated below. It is shown in the figure that at 32k output length, Ring-lite-linear-preview achieves 2.2× throughput of Ring-lite.
 <p align="center">
-    <img src="https://modelscope.cn/api/v1/models/inclusionAI/Ring-lite-linear-preview/repo?Revision=master&FilePath=throughput.png&View=true" width="600"/>
 <p>
 Additionally, to illustrate the advantage in inference speed, we present a comparison between Ring-lite-linear-preview and softmax-attention-based Ring-lite under a batch size of 64 and an output length of 16k (60x speedup). It can be observed that the KV cache usage of Ring-lite-linear-preview is nearly 1/6 that of Ring-lite, and the E2E time is reduced by 27.24% compared with Ring-lite.
 <p align="center">
-    <img src="https://modelscope.cn/api/v1/models/inclusionAI/Ring-lite-linear-preview/repo?Revision=master&FilePath=inference_speed.gif&View=true" width="600"/>
 <p>
 More details will be reported in our technical report [TBD]

 # Ring-lite-linear-preview
 <p align="center">
+    <img src="https://huggingface.co/inclusionAI/Ring-lite-linear-preview/blob/main/ant-bailing.png" width="100"/>
 <p>
 <p align="center">
 To evaluate the generation throughput, we deploy Ring-lite-linear and the softmax-attention-based Ring-lite based on vLLM on a single NVIDIA A100 GPU. Specifically, the input sequence length is fixed to 1. The end-to-end (E2E) generation time required for generating output sequences of varying lengths is illustrated below. It is shown in the figure that at 32k output length, Ring-lite-linear-preview achieves 2.2× throughput of Ring-lite.
 <p align="center">
+    <img src="https://huggingface.co/inclusionAI/Ring-lite-linear-preview/blob/main/throughput.png" width="600"/>
 <p>
 Additionally, to illustrate the advantage in inference speed, we present a comparison between Ring-lite-linear-preview and softmax-attention-based Ring-lite under a batch size of 64 and an output length of 16k (60x speedup). It can be observed that the KV cache usage of Ring-lite-linear-preview is nearly 1/6 that of Ring-lite, and the E2E time is reduced by 27.24% compared with Ring-lite.
 <p align="center">
+    <img src="https://huggingface.co/inclusionAI/Ring-lite-linear-preview/blob/main/inference_speed.gif" width="600"/>
 <p>
 More details will be reported in our technical report [TBD]