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
```

kvaishnavi commited on Feb 11

Commit

de94d9a

verified ·

1 Parent(s): 73058b2

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -9

README.md CHANGED Viewed

@@ -23,9 +23,10 @@ huggingface-cli download onnxruntime/DeepSeek-R1-Distill-ONNX --include deepseek
 # Install the CPU package of ONNX Runtime GenAI
 pip install onnxruntime-genai
-# Please adjust the model directory (-m) accordingly
-curl -o https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/model-chat.py
-python model-chat.py -m /path/to/cpu-int4-rtn-block-32-acc-level-4/ -e cpu --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"
 ```
 For CUDA:
@@ -37,9 +38,10 @@ huggingface-cli download onnxruntime/DeepSeek-R1-Distill-ONNX --include deepseek
 # Install the CUDA package of ONNX Runtime GenAI
 pip install onnxruntime-genai-cuda
-# Please adjust the model directory (-m) accordingly
-curl -o https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/model-chat.py
-python model-chat.py -m /path/to/gpu-int4-rtn-block-32/ -e cuda --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"
 ```
 For DirectML:
@@ -51,9 +53,10 @@ huggingface-cli download onnxruntime/DeepSeek-R1-Distill-ONNX --include deepseek
 # Install the DirectML package of ONNX Runtime GenAI
 pip install onnxruntime-genai-directml
-# Please adjust the model directory (-m) accordingly
-curl -o https://raw.githubusercontent.com/microsoft/onnxruntime-genai/refs/heads/main/examples/python/model-chat.py
-python model-chat.py -m /path/to/gpu-int4-rtn-block-32/ -e dml --chat_template "<|begin▁of▁sentence|><|User|>{input}<|Assistant|>"
 ```

 # Install the CPU package of ONNX Runtime GenAI
 pip install onnxruntime-genai
+# Please adjust the model directory (-m) accordingly
+curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
+curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-chat.py -o model-chat.py
+python model-chat.py -m /path/to/cpu-int4-rtn-block-32-acc-level-4/ -e cpu
 ```
 For CUDA:
 # Install the CUDA package of ONNX Runtime GenAI
 pip install onnxruntime-genai-cuda
+# Please adjust the model directory (-m) accordingly
+curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
+curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-chat.py -o model-chat.py
+python model-chat.py -m /path/to/gpu-int4-rtn-block-32/ -e cuda
 ```
 For DirectML:
 # Install the DirectML package of ONNX Runtime GenAI
 pip install onnxruntime-genai-directml
+# Please adjust the model directory (-m) accordingly
+curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/common.py -o common.py
+curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/model-chat.py -o model-chat.py
+python model-chat.py -m /path/to/gpu-int4-rtn-block-32/ -e dml
 ```