Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

Documenti analoghi

• FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
  di: Pöppel, Korbinian, et al.
  Pubblicazione: (2024)
• Vision-LSTM: xLSTM as Generic Vision Backbone
  di: Alkin, Benedikt, et al.
  Pubblicazione: (2024)
• xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
  di: Beck, Maximilian, et al.
  Pubblicazione: (2025)
• xLSTM: Extended Long Short-Term Memory
  di: Beck, Maximilian, et al.
  Pubblicazione: (2024)
• A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
  di: Schmied, Thomas, et al.
  Pubblicazione: (2024)