Update README.md

README.md

@@ -5,6 +5,7 @@ tags:
 - diffusion
 - llm
 - text_generation
+library_name: transformers
 ---
 # LLaDA-MoE
 
@@ -64,15 +65,63 @@ tags:
 
 ---
 
-## ⚡ Quickstart
+## ⚡ Infra
+### 1. We highly recommend you generate with [dInfer](https://github.com/inclusionAI/dInfer)（1000+ Tokens/S）
 
-Make sure you have `transformers` and its dependencies installed:
+<p align="center">
+  <img src="https://raw.githubusercontent.com/inclusionAI/dInfer/refs/heads/master/assets/dinfer_tps.png" alt="dInfer v0.1 speedup" width="600">
+  <br>
+  <b>Figure</b>: Display of generation speed
+</p>
+
+On HumanEval, dInfer achieves over 1,100 TPS at batch size 1, and averages more than 800 TPS across six benchmarks on
+a single node with 8 H800 GPUs. 
+#### Install dInfer
+
+```
+git clone https://github.com/inclusionAI/dInfer.git
+cd dInfer
+pip install .
+```
+
+#### Convert to FusedMoE
+
+Use the conversion tool to fuse the experts.
 
 ```bash
-pip install transformers torch
+# From repo root
+python tools/transfer.py \
+  --input  /path/to/LLaDA-MoE-7B-A1B-Instruct \
+  --output /path/to/LLaDA-MoE-7B-A1B-Instruct-fused
+```
+
+#### Use the model in dInfer
+
+```python
+import torch
+from transformers import AutoTokenizer
+
+from dinfer.model import AutoModelForCausalLM
+from dinfer.model import FusedOlmoeForCausalLM
+from dinfer import BlockIteratorFactory, KVCacheFactory
+from dinfer import ThresholdParallelDecoder, BlockWiseDiffusionLLM
+
+m = "/path/to/LLaDA-MoE-7B-A1B-Instruct-fused"
+tok = AutoTokenizer.from_pretrained(m, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(m, trust_remote_code=True, torch_dtype="bfloat16")
+
+decoder = ThresholdParallelDecoder(0, threshold=0.9)
+dllm = BlockWiseDiffusionLLM(model, decoder, BlockIteratorFactory(True), cache_factory=KVCacheFactory('dual'))
+
+prompt = "Lily can run 12 kilometers per hour for 4 hours. After that, she can run 6 kilometers per hour. How many kilometers can she run in 8 hours?"
+input_ids = tokenizer(prompt)['input_ids']
+input_ids = torch.tensor(input_ids).to(device).unsqueeze(0)
+res = dllm.generate(input_ids, gen_length=gen_len, block_length=block_len)
 ```
 
-You can then load the model using the AutoModelForCausalLM and AutoTokenizer classes:
+### 2. No Speedup: transformers
+
+Make sure you have `transformers` and its dependencies installed:
 
 ```python
 import torch
@@ -163,6 +212,11 @@ model = AutoModel.from_pretrained('inclusionAI/LLaDA-MoE-7B-A1B-Instruct', trust
 tokenizer = AutoTokenizer.from_pretrained('inclusionAI/LLaDA-MoE-7B-A1B-Instruct', trust_remote_code=True)
 
 prompt = "Lily can run 12 kilometers per hour for 4 hours. After that, she runs 6 kilometers per hour. How many kilometers can she run in 8 hours?"
+m = [
+    {"role": "system", "content": "You are a helpful AI assistant."},
+    {"role": "user", "content": prompt}
+]
+prompt = tokenizer.apply_chat_template(m, add_generation_prompt=True, tokenize=False)
 
 input_ids = tokenizer(prompt)['input_ids']
 input_ids = torch.tensor(input_ids).to(device).unsqueeze(0)
@@ -176,10 +230,17 @@ print(tokenizer.batch_decode(text[:, input_ids.shape[1]:], skip_special_tokens=F
 ```
 
 
-## 📚 Citation (Coming Soon)
+## 📚 Citation [LLaDA-MoE](https://arxiv.org/abs/2509.24389)
 
-We are preparing the technical report and citation information.  
-Stay tuned — citation details will be available soon.
+If you find LLaDA-MoE useful in your research or applications, please cite our paper:
+```
+@article{zhu2025llada,
+  title={LLaDA-MoE: A Sparse MoE Diffusion Language Model},
+  author={Fengqi Zhu and Zebin You and Yipeng Xing and Zenan Huang and Lin Liu and Yihong Zhuang and Guoshan Lu and Kangyu Wang and Xudong Wang and Lanning Wei and Hongrui Guo and Jiaqi Hu and Wentao Ye and Tieyuan Chen and Chenchen Li and Chengfu Tang and Haibo Feng and Jun Hu and Jun Zhou and Xiaolu Zhang and Zhenzhong Lan and Junbo Zhao and Da Zheng and Chongxuan Li and Jianguo Li and Ji-Rong Wen},
+  journal={arXiv preprint arXiv:2509.24389},
+  year={2025}
+}
+```
 
 ---