Instructions to use inclusionAI/Ring-1T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ring-1T with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ring-1T", 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-1T", trust_remote_code=True, dtype="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inclusionAI/Ring-1T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ring-1T"
# 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-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ring-1T

SGLang

How to use inclusionAI/Ring-1T 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-1T" \
    --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-1T",
		"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-1T" \
        --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-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ring-1T with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ring-1T
```

How do you compute the cosine similarity for evaluating the FP8 quantization quality?

#11

by yhh001 - opened Oct 29, 2025

Discussion

yhh001

Oct 29, 2025

Many thanks for the great work!

I was wondering how do you compute the cosine similarity for evaluating the FP8 quantization quality during training. is it per tensor flatten then dot product or per row DP or per column DP?

im0qianqian

Oct 29, 2025

Thank you for your attention!

Taking Y = X @ W.T as an example, we use the mean cosine similarity of each row in the tensor (X or W) before and after FP8 quantization as the distortion metric. During this process, rows with all zero elements will be ignored.

yhh001

Oct 30, 2025

Thank you for your attention!

Taking Y = X @ W.T as an example, we use the mean cosine similarity of each row in the tensor (X or W) before and after FP8 quantization as the distortion metric. During this process, rows with all zero elements will be ignored.

Thank you for the reply!

So I can understand this as cosine similarity of the rows of X and columns of W.T, that perform the Matrix multiply accumulation process?

May I ask if you have any underlying reason that cosine similarity serves as a better metric of quantization quality than Signal-to-Noise Ratio (SNR)?

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