Instructions to use deepseek-ai/DeepSeek-V4-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V4-Flash with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Flash")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-V4-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4-Flash"
# 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-V4-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash

SGLang

How to use deepseek-ai/DeepSeek-V4-Flash 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-V4-Flash" \
    --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-V4-Flash",
		"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-V4-Flash" \
        --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-V4-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V4-Flash with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash
```

use vLLM with 2 DGX Sparks , response broken

#29

by easonchow0419 - opened 8 days ago

Discussion

easonchow0419

8 days ago

docker pull lmxxf/vllm-deepseek-v4-dgx-spark:latest

vllm serve /root/.cache/huggingface/deepseek-v4-flash
--served-model-name deepseek-ai/DeepSeek-V4-Flash
--tensor-parallel-size 2
--pipeline-parallel-size 1
--distributed-executor-backend ray
--gpu-memory-utilization 0.85
--kv-cache-dtype fp8
--block-size 256
--max-model-len 147456
--max-num-seqs 2
--max-num-batched-tokens 4176
--enforce-eager
--trust-remote-code
--tool-call-parser deepseek_v4
--enable-auto-tool-choice
--reasoning-parser deepseek_v4
--tokenizer-mode deepseek_v4
--enable-expert-parallel
--no-enable-flashinfer-autotune
--host 0.0.0.0 --port 8000 \

http://localhost:8000/v1/chat/completions
{
"model": "deepseek-ai/DeepSeek-V4-Flash",
"messages": [
{"role": "user", "content": "Hello can you advice a food you like ?"}
],
"max_tokens": 50,
"temperature": 1
}

{
"id": "chatcmpl-96241ab2ba746885",
"object": "chat.completion",
"created": 1778463765,
"model": "deepseek-ai/DeepSeek-V4-Flash",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Of,»\n OTHER(other �フィ(sh”\n OTHER,\n,\n,\n OTHERAND AND ______( then \( AND . ✅ THE C WORD AND ․ AFTER‥」 After‥ . . . . . . . . . . . . . .",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null
},
"logprobs": null,
"finish_reason": "length",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.1.dev1+g7a34ed538-tp2-ep-dc20b174",
"usage": {
"prompt_tokens": 13,
"total_tokens": 63,
"completion_tokens": 50,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}

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

use vLLM with 2 DGX Sparks , response broken

docker pull lmxxf/vllm-deepseek-v4-dgx-spark:latest

http://localhost:8000/v1/chat/completions{ "model": "deepseek-ai/DeepSeek-V4-Flash", "messages": [ {"role": "user", "content": "Hello can you advice a food you like ?"} ], "max_tokens": 50, "temperature": 1}

http://localhost:8000/v1/chat/completions
{
"model": "deepseek-ai/DeepSeek-V4-Flash",
"messages": [
{"role": "user", "content": "Hello can you advice a food you like ?"}
],
"max_tokens": 50,
"temperature": 1
}