Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
☆883Jan 28, 2026Updated last month
Alternatives and similar repositories for Fast-dLLM
Users that are interested in Fast-dLLM are comparing it to the libraries listed below
Sorting:
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆198Nov 17, 2025Updated 4 months ago
- Official PyTorch implementation for "Large Language Diffusion Models"☆3,682Nov 12, 2025Updated 4 months ago
- ☆91Nov 17, 2025Updated 4 months ago
- Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"☆419Jan 26, 2026Updated last month
- Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.☆554Mar 1, 2026Updated 2 weeks ago
- Dream 7B, a large diffusion language model☆1,198Nov 21, 2025Updated 4 months ago
- A Collection of Papers on Diffusion Language Models☆160Sep 15, 2025Updated 6 months ago
- MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)☆1,610Feb 14, 2026Updated last month
- Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference☆246Feb 3, 2026Updated last month
- Source code for paper "Empirical Analysis of Decoding Biases in Masked Diffusion Models"☆39Jan 11, 2026Updated 2 months ago
- [ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.☆464Jan 28, 2026Updated last month
- ☆332Dec 16, 2025Updated 3 months ago
- The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".☆871Mar 10, 2026Updated last week
- SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）☆342Updated this week
- [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models☆130May 22, 2025Updated 10 months ago
- [Arxiv] Discrete Diffusion in Large Language and Multimodal Models: A Survey☆374Nov 1, 2025Updated 4 months ago
- ☆55Jun 4, 2025Updated 9 months ago
- Official PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Princ…☆41Jul 18, 2025Updated 8 months ago
- Esoteric Language Models☆114Feb 8, 2026Updated last month
- [ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models☆979Jul 10, 2025Updated 8 months ago
- Official implementation of "DPad: Efficient Diffusion Language Models with Suffix Dropout"☆57Feb 13, 2026Updated last month
- Official Implementation of LaViDa: :A Large Diffusion Language Model for Multimodal Understanding☆199Dec 17, 2025Updated 3 months ago
- Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)☆700Sep 24, 2025Updated 5 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,145Mar 15, 2026Updated last week
- [ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models☆378May 31, 2025Updated 9 months ago
- ☆114Sep 13, 2025Updated 6 months ago
- Implementation of "Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models" [NeurIPS 2025]☆75Dec 17, 2025Updated 3 months ago
- [AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs☆55Dec 7, 2025Updated 3 months ago
- Easy and Efficient dLLM Fine-Tuning☆235Mar 2, 2026Updated 2 weeks ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,145Mar 9, 2026Updated last week
- Sequential Diffusion Language Model (SDLM) enhances pre-trained autoregressive language models by adaptively determining generation lengt…☆92Dec 27, 2025Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆818Mar 6, 2025Updated last year
- ☆154Feb 25, 2026Updated 3 weeks ago
- A lightweight Inference Engine built for block diffusion models☆42Dec 9, 2025Updated 3 months ago
- Dimple, the first Discrete Diffusion Multimodal Large Language Model☆115Jul 9, 2025Updated 8 months ago
- paper list, tutorial, and nano code snippet for Diffusion Large Language Models.☆156Jan 19, 2026Updated 2 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆153Mar 21, 2025Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,229Feb 20, 2026Updated last month
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,630Updated this week