Tag: Multimodality

All the articles with the tag "Multimodality".

• Splitwiser: Efficient LM inference with constrained resources

  Published: 11 May, 2025 |  at  11:14 AM

  

  60.85 🤔

  Splitwiser introduces a method to split LLM inference phases on a single GPU using multiprocessing and NVIDIA MPS, achieving modest latency reductions (up to 18.2%) and throughput improvements (up to 1.42x) on Huggingface and vLLM pipelines, though constrained by overheads and scalability issues.

• RWKV-X: A Linear Complexity Hybrid Language Model

  Published: 4 May, 2025 |  at  04:32 PM

  

  87.80 👍

  本文提出RWKV-X，一种线性复杂度的混合语言模型，通过结合RWKV和稀疏注意力机制，提升长上下文建模能力，同时保持高效性和短上下文性能。