Instructions to use inclusionAI/Ling-3.0-flash-dspark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ling-3.0-flash-dspark with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ling-3.0-flash-dspark")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("inclusionAI/Ling-3.0-flash-dspark")
model = AutoModel.from_pretrained("inclusionAI/Ling-3.0-flash-dspark", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ling-3.0-flash-dspark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ling-3.0-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": "inclusionAI/Ling-3.0-flash-dspark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/inclusionAI/Ling-3.0-flash-dspark

SGLang

How to use inclusionAI/Ling-3.0-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 "inclusionAI/Ling-3.0-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": "inclusionAI/Ling-3.0-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 "inclusionAI/Ling-3.0-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": "inclusionAI/Ling-3.0-flash-dspark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use inclusionAI/Ling-3.0-flash-dspark with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ling-3.0-flash-dspark
```

Ling3-DSpark

A DSpark speculator for Ling3. DSpark extends DFlash with target-model auxiliary features and a confidence head that dynamically chooses the number of draft tokens. The model was trained with SpecForge and is served with SGLang.

Model specifications

Target model: Ling-3.0-flash
Draft parameters: 1,363,707,905 (1.36B)
Draft weight dtype: BF16
Hidden size: 2,560
Transformer layers: 5 full-attention layers
Attention: MHA with 32 query heads and 32 key/value heads
Target auxiliary feature layers: 1, 11, 23, 29, 35
Confidence head: vanilla Markov head, rank 256
DSpark block size: 8 draft tokens (verify width 9, including the target bonus token)
Maximum position embeddings: 262,144

Acceptance length

Acceptance length is the mean number of tokens accepted per speculative verification step, including the target bonus token.

Workload	Acceptance length
GSM8K	6.40
MATH-500	6.29
AIME 2025	5.56
HumanEval	6.57
MBPP	6.34
LiveCodeBench	5.33
MT-Bench	3.92
Alpaca	3.51
Arena-Hard-v2	3.72

The macro mean across the nine workload means is 5.29.

Serving with SGLang

Launch recipes for this draft on every supported hardware/quantization cell — including the required --linear-replayssm-cache-len sizing — with measured speed and accuracy, are in the SGLang Ling-3.0-flash cookbook.

Use an SGLang version with DSPARK support. Replace the model paths and tensor-parallel size with values appropriate for your deployment:

sglang serve \
  --trust-remote-code \
  --model-path <LING3_MODEL_PATH> \
  --tp-size <TP_SIZE> \
  --speculative-algorithm DSPARK \
  --speculative-draft-model-path <LING3_DSPARK_MODEL_PATH> \
  ......

Downloads last month: 71

Safetensors

Model size

1B params

Tensor type

BF16