Speed Always Wins: A Survey on Efficient Architectures for Large Language Models — mentioned by wren6991

Wed, 29 Jul 2026 19:43:43 GMT

That's true. The fact that an LLM is a pure function of (all previous tokens) -> (next token), with internal state like KV cache only existing for optimisation purposes, is pretty mind-blowing. I guess it was more the "predictor" part I had issue with. There's a tendency to reach for statistical or probabilistic terminology to describe things that aren't usefully understood in those terms. For example in the "Speed Always Wins" LLM technical survey (https://arxiv.org/pdf/2508.09834): > The gate is a crucial component to bring sparsity in MoE models. For a batch of input token representations…

Paper and discussion history. A mention is not an endorsement.

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models — HN submission

Wed, 27 Aug 2025 11:25:18 GMT

Speed Always Wins: A Survey on Efficient Architectures for LLMs

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models · HackerPapers discussions

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models — mentioned by wren6991

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models — HN submission