Hackernews posts about Mamba/Transformer
- Nemotron 3 Ultra: Open Moe Hybrid Mamba-Transformer for Agentic Reasoning [pdf] (research.nvidia.com)
- Nvidia: Nemotron 3 Super (developer.nvidia.com)
- Nemotron-H: A Family of Accurate, Efficient Hybrid Mamba-Transformer Models (research.nvidia.com)
- Nemotron 3 Super: An Open Hybrid Mamba-Transformer Moe for Agentic Reasoning (developer.nvidia.com)
- Mamba (Transformer Alternative): The Future of LLMs? (lazyprogrammer.me)
- Nvidia debuts Nemotron 3 with hybrid MoE and Mamba-Transformer (venturebeat.com)
- Mamba 3 matches Transformer performance at reduced latency (venturebeat.com)
- Show HN: Linear RNN/Reservoir hybrid generative model, one C file (no deps.) (raw.githubusercontent.com)
- The Mamba in the Llama (distilling from transformers) (twitter.com)
- Show HN: New Cartesia Text-to-Speech Model (www.cartesia.ai)