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)
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-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
```

无辅助损失专家偏置代码实现的小问题 A Small Issue in the Code Implementation of Auxiliary-Loss-Free Load Balancing Expert Bias

#89

by liyang31163150 - opened Feb 28, 2025

Discussion

liyang31163150

Feb 28, 2025

在实现无辅助损失负载均衡（Auxiliary-Loss-Free Load Balancing）的专家偏置项时，代码中采用了如下定义： self.e_score_correction_bias = nn.Parameter(torch.empty((self.n_routed_experts)))。个人认为这一实现可能存在细微的问题。我们知道专家偏置项的更新是基于历史负载均衡表现做动态调整，而非通过反向传播来更新参数值。因此，建议通过设置 requires_grad=False 显式禁用该参数的梯度计算，以实现梯度截断。这样可以确保优化器不会更新该参数，从而使其更新机制与设计意图保持一致。不知道个人理解是否有误？

In the implementation of the expert bias for Auxiliary-Loss-Free Load Balancing, the code defines it as follows: self.e_score_correction_bias = nn.Parameter(torch.empty((self.n_routed_experts))).
Personally, I believe there might be a subtle issue with this approach. It is understood that the update of the expert bias is dynamically adjusted based on historical load balancing performance, rather than being updated through back propagation. Therefore, I suggest explicitly disabling gradient computation for this parameter by setting "requires_grad=False" to enforce gradient stop. This ensures that the optimizer does not update the parameter, aligning its update mechanism with the intended design.
I’m not sure if my understanding is correct?

xujfcn

Feb 24

If you're looking for an easy way to access this model via API, you can use Crazyrouter — it provides an OpenAI-compatible endpoint for 600+ models including this one. Just pip install openai and change the base URL.

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