Search papers, labs, and topics across Lattice.
4
3
9
27
Switching between autoregressive and diffusion modes allows Nemotron-Labs-Diffusion to achieve unprecedented throughput and efficiency in language modeling.
Achieving six times the inference throughput of current LLMs while maintaining accuracy, Nemotron 3 Ultra redefines performance benchmarks for agentic reasoning tasks.
Stop forcing your multimodal encoders to inherit suboptimal LLM parallelism strategies: heterogeneous parallelism unlocks up to 49% higher TFLOPS/GPU.
Multimodal models can now achieve state-of-the-art performance in real-world tasks like document understanding and audio-video comprehension with significantly reduced inference latency thanks to novel token-reduction techniques.
