Instructions to use deepseek-ai/DeepSeek-V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V3 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3", 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-V3", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3", trust_remote_code=True, device_map="auto")
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-V3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V3"
# 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-V3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V3

SGLang

How to use deepseek-ai/DeepSeek-V3 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-V3" \
    --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-V3",
		"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-V3" \
        --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-V3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V3 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V3
```

vLLM on A100s

#41

by fsaudm - opened Jan 6, 2025

Discussion

fsaudm

Jan 6, 2025

Im running into an CUDA OOM issue.. though Im trying to serve a bf16 version I found here on HF (opensourcerelease/DeepSeek-V3-bf16) since I have A100s.

I have access to only A100s, and I have 9 nodes with 2 GPUs (so 18 A100s of 80 GBs, 1440 GBs in total). I though 685B params would be somewhere around 1350 GBs plus some overhead for half precision. Any thoughts? I am also trying to unload to CPU but still getting CUDA OOM...

vllm serve opensourcerelease/DeepSeek-V3-bf16
--dtype bfloat16
--host 0.0.0.0
--port 5000
--gpu-memory-utilization 0.7
--cpu-offload-gb 540
--tensor-parallel-size 2
--pipeline-parallel-size 9
--trust-remote-code

any thoughts? pls help :(

HuggingLianWang

Jan 6, 2025

•

edited Jan 6, 2025

Mark, I also encountered a similar problem.
The official provided pipelines for H series graphics cards, but it seems that there is no example for A100 series cards.
Also, fp8 model requires 16 cards of h20, I thought the bf16 model required ~32 cards of a100 (https://huggingface.co/opensourcerelease/DeepSeek-V3-bf16/discussions/5).
Has anyone tried quantization?