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

Libraries

How to use deepseek-ai/DeepSeek-R1 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1

SGLang

How to use deepseek-ai/DeepSeek-R1 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 "deepseek-ai/DeepSeek-R1" \
    --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": "deepseek-ai/DeepSeek-R1",
		"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 "deepseek-ai/DeepSeek-R1" \
        --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": "deepseek-ai/DeepSeek-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1
```

Deploying production ready service with Unsloth GGUF quants on your AWS account. (4 x L40S)

#171

by samagra-tensorfuse - opened Feb 24, 2025

Discussion

samagra-tensorfuse

Feb 24, 2025

Hi People

In the past few weeks we have been doing tons of PoCs with enterprises trying to deploy DeepSeek R1. The most popular combination was the Unsloth GGUF
quants on 4xL40S.

We just dropped the guide to deploy it on serverless GPUs on your own cloud: https://tensorfuse.io/docs/guides/integrations/llama_cpp

Single request tok/sec - 24 tok/sec

Context size - 5k

agam30

Feb 24, 2025

We also ran multiple experiments to figure out the right combination of context size fit and tps. You can modify the the "--n-gpu-layers" and "--ctx-size" paramters to calculate tokens per second for each scenario, here are the results -

GPU Layers 30 , context 10k, speed 6.3 t/s
GPU Layers 40, context 10k, speed 8.5 t/s
GPU Layers 50, context 10k , speed 12 t/s
At GPU layers > 50 , 10k context window will not fit.

ghostplant

Feb 24, 2025

Is it FP8 based, or Q4 based?

MrDevolver

Feb 24, 2025

If I had Deepseek R1 running at 6.3 t/s with context 10k, all running locally I'd be happy and probably wouldn't even touch online models or very rarely.
Unfortunately that's not possible on consumer PC's, but on the other hand for servers it sounds too slow... 🤷‍♂️

samagra-tensorfuse

Feb 24, 2025

Is it FP8 based, or Q4 based?

@ghostplant It is a 1.58 bit dynamic quant.

If I had Deepseek R1 running at 6.3 t/s with context 10k, all running locally I'd be happy and probably wouldn't even touch online models or very rarely.
Unfortunately that's not possible on consumer PC's, but on the other hand for servers it sounds too slow... 🤷‍♂️

@MrDevolver You can increase the speed by increasing the number of GPUs. Max I have achieved is arouns 70 tok/sec on L40S

I also tried running on CPU only machines and I was getting 5 tokens per second. If you have a decent mac you can run it at 6.3 tokens per second.

ghostplant

Feb 24, 2025

•

edited Feb 24, 2025

Does Quat1B still outperform o1-mini? If not, why not using 32B distilled what only costs 1 GPU?

MrDevolver

Feb 24, 2025

Is Q1 still outperform o1-mini? If no, why not using 32B version?

Imho, low quant of bigger model is still better than highest quant of smaller model.

ghostplant

Feb 24, 2025

Is Q1 still outperform o1-mini? If no, why not using 32B version?

Imho, low quant of bigger model is still better than highest quant of smaller model.

Is there any formal comparison to show their performance with Distilled-Qwen-32B?

zlatinb

Feb 24, 2025

Subjectively the 2.5bit quantization outperforms handily the llama 70B distil in reasoning quality. The 70B distil is much faster though...

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