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

Libraries

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

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Flash-DSpark")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V4-Flash-DSpark 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-DSpark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use deepseek-ai/DeepSeek-V4-Flash-DSpark 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-DSpark" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-DSpark" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Update README.md to add vLLM snippet

by xianbao - opened Jul 3

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+18

-0

Files changed (1) hide show

README.md +18 -0

README.md CHANGED Viewed

@@ -217,6 +217,24 @@ tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-
 tokens = tokenizer.encode(prompt)
 ```
 ## How to Run Locally
 Please refer to the [inference](inference/README.md) folder for detailed instructions on running DeepSeek-V4 locally, including model weight conversion and interactive chat demos.

 tokens = tokenizer.encode(prompt)
 ```
+## How to Run with vLLM
+DSpark speculative decoding is enabled with a single flag — add --speculative-config with method: dspark to your vLLM launch command:
+`--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'`
+For example, the command below serves the model with vLLM on a single 4×GB300 node.
+See the [vLLM recipe](https://recipes.vllm.ai/deepseek-ai/DeepSeek-V4-Flash?hardware=b300&features=tool_calling,reasoning) for detailed instructions and other hardware configurations.
+```bash
+vllm serve deepseek-ai/DeepSeek-V4-Flash-DSpark \
+  --trust-remote-code --kv-cache-dtype fp8 --block-size 256 \
+  --data-parallel-size 4 --enable-expert-parallel \
+  --moe-backend deep_gemm_mega_moe \
+  --attention-config '{"use_fp4_indexer_cache": true}' \
+  --speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'
+```
 ## How to Run Locally
 Please refer to the [inference](inference/README.md) folder for detailed instructions on running DeepSeek-V4 locally, including model weight conversion and interactive chat demos.