…9, 8699, 8537, 8926) - Add TaoMate-H3 realtime AR-diffusion streaming and an LTX 2.5 single-stage text-to-audio pipeline. ( 8268, 6489) - Add optional single-stage Qwen3-

…ate-async training across both autoregressive and diffusion pipelines, including Qwen3-Omni audio and text fully-async RL, the dedicated Omni separate-async V1 trainer, M

…lash experts for LoRA. - Speculative and discrete-diffusion training. DFlash 2, additional Kimi K3 and DeepSeek-V4.1 draft-training paths, streaming EAGLE-3 feature compo

…history. ( 7413, 7633) Extended scheduler-managed diffusion KV into cross-stage transfer and reuse , adding native Mooncake AR-to-DiT handoff, KV prefetch, and HunyuanIma

…ucture. It is a hybrid of an autoregressive and a diffusion stage: an 8B Qwen3-based global language model predicts one semantic audio token per frame while a small depth

…ns a Qwen-style language model in parallel with a diffusion generation pathway, joined by a 3D multimodal RoPE. This release also lands video-to-video and action-conditio