view article Article Native-speed vLLM transformers modeling backend hmellor, lysandre • 15 days ago • 58
view article Article Hugging Face and Cerebras bring Gemma 4 to real-time voice AI +2 A-Mahla, andito, lvwerra, vyassaurabh • 22 days ago • 83
Nemotron-Labs-Diffusion Collection A Tri-Mode Language Model Family Unifying Autoregressive, Diffusion, and Self-Speculation Decoding • 7 items • Updated 6 days ago • 52