[ICML 2026] d3LLM: Ultra-Fast Diffusion LLM 🚀
llama.cpp fork for long-context & speculation on consumer GPUs: TurboQuant KV cache (KTQ+VTQ, 2.78 bpw), MTP+n-gram speculation (2.28× on Qwen3.6-35B-A3B), and coherent 2-bit DiffusionGemma (26B-A4B text-diffusion MoE) on a single 12 GB card.
Minimal quickstart fork of the LLaDA repository. Watch text diffusion with a single line of code (& flag).
[ACL 2025 Oral] Official code for paper "Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion Processes".
A text diffusion model based on DDPM operating in embedding space, generating coherent sequences by denoising continuous latent representations instead of discrete tokens.
Learn your codebases through self-quizzing and study. Track your knowledge coverage over time.
SwiftUI Demos for Inception Labs Diffusion Model
A modular library for training language models from scratch: autoregressive transformers, text diffusion, and alignment.
Add a description, image, and links to the text-diffusion topic page so that developers can more easily learn about it.
To associate your repository with the text-diffusion topic, visit your repo's landing page and select "manage topics."