Instructions to use onnxruntime/DeepSeek-R1-Distill-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onnxruntime/DeepSeek-R1-Distill-ONNX with Transformers:

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

pipe = pipeline("text-generation", model="onnxruntime/DeepSeek-R1-Distill-ONNX")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("onnxruntime/DeepSeek-R1-Distill-ONNX", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use onnxruntime/DeepSeek-R1-Distill-ONNX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "onnxruntime/DeepSeek-R1-Distill-ONNX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnxruntime/DeepSeek-R1-Distill-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/onnxruntime/DeepSeek-R1-Distill-ONNX

SGLang

How to use onnxruntime/DeepSeek-R1-Distill-ONNX 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 "onnxruntime/DeepSeek-R1-Distill-ONNX" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnxruntime/DeepSeek-R1-Distill-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "onnxruntime/DeepSeek-R1-Distill-ONNX" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnxruntime/DeepSeek-R1-Distill-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use onnxruntime/DeepSeek-R1-Distill-ONNX with Docker Model Runner:
```
docker model run hf.co/onnxruntime/DeepSeek-R1-Distill-ONNX
```

parinitarahi commited on Feb 15, 2025

Commit

8598fe0

verified ·

1 Parent(s): 6f5c8e9

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ license: mit
 This repository hosts the optimized versions of [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/) and [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/) to accelerate inference with ONNX Runtime.
 Optimized models are published here in [ONNX](https://onnx.ai) format to run with [ONNX Runtime](https://onnxruntime.ai/) on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets.
-To easily get started with the model, you can use our newly introduced ONNX Runtime Generate() API.
 ```bash
 # Download the model directly using the huggingface cli

 This repository hosts the optimized versions of [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/) and [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/) to accelerate inference with ONNX Runtime.
 Optimized models are published here in [ONNX](https://onnx.ai) format to run with [ONNX Runtime](https://onnxruntime.ai/) on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets.
+To easily get started with the model, you can use our ONNX Runtime Generate() API. See instructions [here](https://github.com/microsoft/onnxruntime/blob/gh-pages/docs/genai/tutorials/deepseek-python.md)
 ```bash
 # Download the model directly using the huggingface cli