4 papers
Fast Recovery for LLM Serving via Decoupled Device Memory Lifetime in Dynamo
Schwinn Saereesitthipitak, Mohammed Abdulwahhab, Hannah Zhang +6
Large language model (LLM) inference replicas run across tightly coupled GPUs and serve traffic continuously for weeks. Hardware and software failures are therefore inevitable, and…
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
Yonggan Fu, Lexington Whalen, Abhinav Garg +23
We introduce Nemotron-Labs-Diffusion, a tri-mode language model (LM) that unifies AR, diffusion, and self-speculation decoding within a single architecture. Trained with a joint AR…
Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
Yonggan Fu, Lexington Whalen, Zhifan Ye +11
Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning efficiency lags behind that of autore…
Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
Yonggan Fu, Xin Dong, Shizhe Diao +12
Efficient deployment of small language models (SLMs) is essential for numerous real-world applications with stringent latency constraints. While previous work on SLM design has pri…