LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding — mentioned by mazd

Wed, 29 May 2024 01:21:23 GMT

I strongly agree! alphaXiv (https://alphaxiv.org/) is a discussion layer on top of arXiv, and it's starting to gain a lot of traction. You can replace the arXiv URL with "alphaXiv" to get to the discussion: https://arxiv.org/abs/2404.16710 → https://alphaxiv.org/abs/2404.16710 Disclaimer: I'm currently helping out with alphaXiv -- it's a fun project out of Stanford

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

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding — HN submission

Fri, 26 Apr 2024 17:42:56 GMT

Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding · HackerPapers discussions

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding — mentioned by mazd

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding — HN submission