Understand this story
On October 10, 2025, Ant inclusionAI open-sourced the first version of dInfer, an inference framework for diffusion language models (dLLM). According to the introduction of its new GitHub repository, the framework splits inference into four modules: the model, the diffusion iteration manager, the decoder, and the KV-cache manager, and it supports batched inference and is compatible with the LLaDA, LLaDA-MoE, and LLaDA2 series. In terms of performance, on a single 8×H800 node, LLaDA-MoE exceeds 1,100 TPS on HumanEval at batch size 1, averages 800+ TPS across six benchmarks, and is 10 times faster than Fast-dLLM while maintaining accuracy. There are currently no public facts regarding further development progress.
AI-generated from public reports
Latest development · Report
Ant inclusionAI Open-Sources dInfer: An Efficient Inference Framework for Diffusion Language ModelsDevelopments
1 confirmed developments
inclusionAI open-sources the dInfer diffusion language model inference framework
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 3
Ant inclusionAI: New GitHub RepositoryFirst-party
Ant inclusionAI Open-Sources dInfer: An Efficient Inference Framework for Diffusion Language Models
Ant inclusionAI has open-sourced dInfer, an efficient inference framework for diffusion language models (dLLMs) that splits inference into four modules—the model, the diffusion iteration manager, the decoder, and the KV-cache manager—and supports batched inference. It supports the LLaDA, LLaDA-MoE, and LLaDA2 series; on a single 8×H800 node, LLaDA-MoE exceeds 1,100 TPS on HumanEval at batch size 1 and averages 800+ TPS across six benchmarks, 10× faster than Fast-dLLM while maintaining accuracy.