DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation Paper • 2502.03930 • Published Feb 6, 2025 • 2
Qwen3.8 Collection Qwen3.8 in NVFP4 (W4A4) — production checkpoints plus DSpark drafts for speculative decoding, built for SGLang. Recipes: https://cookbook.sglang.ai • 4 items • Updated 7 days ago • 4