Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length · HackerPapers discussions

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — mentioned by underlines

Wed, 17 Apr 2024 21:01:48 GMT

tons and tons of papers, most of them had some disadvantages. Can't have the cake and eat it too: https://arxiv.org/html/2404.08801v1 Meta Megalodon https://arxiv.org/html/2404.07143v1 Google Infini-Attention https://arxiv.org/html/2402.13753v1 LongRoPE and a ton more

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

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — HN submission

Tue, 16 Apr 2024 17:40:47 GMT

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

168 points; 28 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — HN submission

Tue, 16 Apr 2024 09:11:28 GMT

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

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

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — HN submission

Tue, 16 Apr 2024 09:10:41 GMT

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

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