Instructions to use Zigeng/dParallel-LLaDA-8B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zigeng/dParallel-LLaDA-8B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Zigeng/dParallel-LLaDA-8B-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Zigeng/dParallel-LLaDA-8B-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Zigeng/dParallel-LLaDA-8B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zigeng/dParallel-LLaDA-8B-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zigeng/dParallel-LLaDA-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zigeng/dParallel-LLaDA-8B-instruct

SGLang

How to use Zigeng/dParallel-LLaDA-8B-instruct 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 "Zigeng/dParallel-LLaDA-8B-instruct" \
    --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": "Zigeng/dParallel-LLaDA-8B-instruct",
		"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 "Zigeng/dParallel-LLaDA-8B-instruct" \
        --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": "Zigeng/dParallel-LLaDA-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zigeng/dParallel-LLaDA-8B-instruct with Docker Model Runner:
```
docker model run hf.co/Zigeng/dParallel-LLaDA-8B-instruct
```

Zigeng commited on Sep 30, 2025

Commit

b50451d

verified ·

1 Parent(s): 71d408c

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -5

README.md CHANGED Viewed

@@ -3,6 +3,7 @@ license: mit
 ---
 <div align="center">
 <h1>🚀 dParallel: Learnable Parallel Decoding for dLLMs</h1>
   <div align="center">
@@ -12,7 +13,7 @@ license: mit
   <a href="https://github.com/czg1225/dParallel">
     <img src="https://img.shields.io/badge/Paper-Arxiv-darkred.svg" alt="Paper">
   </a>
-  <a href="https://huggingface.co/Zigeng/dParallel-LLaDA-8b-instruct">
     <img src="https://img.shields.io/badge/HuggingFace-Model-FFB000.svg" alt="Project">
   </a>
   <a href="https://huggingface.co/datasets/Zigeng/dParallel_LLaDA_Distill_Data">
@@ -53,7 +54,7 @@ We introduce dParallel, a simple and effective method that unlocks the inherent
     </tr>
     <tr>
       <td>🤖 <strong>Model</strong></td>
-      <td><a href="https://huggingface.co/Zigeng/dParallel-LLaDA-8b-instruct">dParallel-LLaDA-8b-instruct</a></td>
     </tr>
     <tr>
       <td>📊 <strong>Data</strong></td>
@@ -83,8 +84,8 @@ from generate import generate
 import torch
 device = 'cuda'
-model = LLaDAModelLM.from_pretrained('Zigeng/dParallel-LLaDA-8b-instruct', trust_remote_code=True, torch_dtype=torch.bfloat16).to(device).eval()
-tokenizer = AutoTokenizer.from_pretrained('Zigeng/dParallel-LLaDA-8b-instruct', trust_remote_code=True)
 prompt = "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? Please reason step by step, and put your final answer within \\boxed{}."
@@ -136,4 +137,11 @@ Our code builds on [LLaDA](https://github.com/ML-GSAI/LLaDA), [Dream](https://gi
 ## Citation
 If our research assists your work, please give us a star ⭐ or cite us using:
 ```
-```

 ---
 <div align="center">
 <h1>🚀 dParallel: Learnable Parallel Decoding for dLLMs</h1>
   <div align="center">
   <a href="https://github.com/czg1225/dParallel">
     <img src="https://img.shields.io/badge/Paper-Arxiv-darkred.svg" alt="Paper">
   </a>
+  <a href="https://huggingface.co/Zigeng/dParallel-LLaDA-8B-instruct">
     <img src="https://img.shields.io/badge/HuggingFace-Model-FFB000.svg" alt="Project">
   </a>
   <a href="https://huggingface.co/datasets/Zigeng/dParallel_LLaDA_Distill_Data">
     </tr>
     <tr>
       <td>🤖 <strong>Model</strong></td>
+      <td><a href="https://huggingface.co/Zigeng/dParallel-LLaDA-8B-instruct">dParallel-LLaDA-8b-instruct</a></td>
     </tr>
     <tr>
       <td>📊 <strong>Data</strong></td>
 import torch
 device = 'cuda'
+model = LLaDAModelLM.from_pretrained('Zigeng/dParallel-LLaDA-8B-instruct', trust_remote_code=True, torch_dtype=torch.bfloat16).to(device).eval()
+tokenizer = AutoTokenizer.from_pretrained('Zigeng/dParallel-LLaDA-8B-instruct', trust_remote_code=True)
 prompt = "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? Please reason step by step, and put your final answer within \\boxed{}."
 ## Citation
 If our research assists your work, please give us a star ⭐ or cite us using:
 ```
+```