inclusionAI/dInfer

Local inference for diffusion language models (LLaDA, Dream), written in Mojo

[NeurIPS 2026] Official implementaion for Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Research code and optimized inference for ALoDLM: Adaptively Looped Diffusion Language Models.

dLLM: Simple Diffusion Language Modeling

Flexible and Pluggable Serving Engine for Diffusion LLMs

A minimal, clean D language interface for running LLM inference using importC around llama.cpp.

RapidLLM is an LLM inference framework with continuous batching, tensor and data parallelism, quantized weights, and with pluggable Triton/CUDA kernels.

A high-throughput and memory-efficient inference and serving engine for LLMs

Easy and Efficient dLLM Fine-Tuning