Instructions to use deepseek-ai/DeepSeek-R1-0528 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1-0528 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-0528", 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-R1-0528", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-0528", 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

vLLM

How to use deepseek-ai/DeepSeek-R1-0528 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1-0528"
# 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-R1-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1-0528

SGLang

How to use deepseek-ai/DeepSeek-R1-0528 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-R1-0528" \
    --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-R1-0528",
		"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-R1-0528" \
        --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-R1-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1-0528 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1-0528
```

How to run 0528version on GPU which don't support FP8

#64

by Micdiane - opened May 29, 2025

Discussion

Micdiane

May 29, 2025

When I run on A800 , it throws error that ValueError: FP8 quantized models is only supported on GPUs with compute capability >= 8.9 (e.g 4090/H100), actual = 8.0

owenqwenllmwine

May 29, 2025

Have you thought to yourself that you do not have enough GPUs to run a 600B parameter model. Unless I missed something?

ghostplant

May 29, 2025

•

edited May 29, 2025

@Micdiane , how many A800s do you have? and what is the memory size per A800? There are solutions for different requirements, but I just want to suggest an optimal choice that fits your case best.

Micdiane

May 30, 2025

@Micdiane , how many A800s do you have? and what is the memory size per A800? There are solutions for different requirements, but I just want to suggest an optimal choice that fits your case best.

2A800, total 2* 80GB. It's a little tough for 600B LLM，hh

ghostplant

May 30, 2025

•

edited May 30, 2025

@Micdiane , how many A800s do you have? and what is the memory size per A800? There are solutions for different requirements, but I just want to suggest an optimal choice that fits your case best.

2A800, total 2* 80GB. It's a little tough for 600B LLM，hh

Looks like even IQ2 cannot work but IQ1. However, IQ1 drops quality a lot, making it less comparable with other smaller models. To enjoy full FP8 precision, seems like CPU + GPU is your only possible choice, which requires 600GB CPU memory to store MoE.

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