Transformers: Quadratic complexity AND Tweet
Descendants partagés
3 Documents
Aran Komatsuzaki sur Twitter : "Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory System Enables LLMs to outperform ChatGPT in scenarios involving ultra-long document summarization or long-term conversations."
Tags:
2023-04-27 A propos
Aran Komatsuzaki sur Twitter : "Scaling Transformer to 1M tokens and beyond with Recurrent Memory Transformer..."
Tags:
2023-04-25 A propos
Amin Karbasi sur Twitter : "...Computation ofTransformer models incurs quadratic time/memory complexities in sequence length... Can we dramatically accelerate them?"
Tags:
2023-02-19 A propos