block-diffusion

paper list, tutorial, and nano code snippet for Diffusion Large Language Models.

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

BlockVid: Block Diffusion for High-Fidelity and Coherent Minute-Long Video Generation

Qwen3.8-27B (Unsloth UD-Q4_K_XL GGUF) served at 37.4 tok/s decode over a 226,048-token context on a single NVIDIA L4 24 GB: llama.cpp with DFlash 2 block-diffusion speculative decoding, a one-line CUDA kernel-routing patch worth 16%, one-command GCP provisioning, quality verification, and a measured account of where the ceiling is.

📚📚Discrete denoising diffusion probabilistic (language) models in MLX

Production-grade fine-tuning & LoRA toolkit for Chatterbox-Flash zero-shot TTS models. Combines parallel block diffusion and FlashInfer acceleration with smart placeholder vocabulary extension supporting languages. Features offline feature preprocessing, Silero VAD silence trimming, zero-padding leakage prevention, and fast voice cloning for custom