Better & Faster Large Language Models via Multi-token Prediction · HackerPapers discussions

Better & Faster Large Language Models via Multi-token Prediction — HN submission

Mon, 19 Oct 2026 18:33:45 GMT

Better and Faster Large Language Models via Multi-Token Prediction (2024)

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

Better & Faster Large Language Models via Multi-token Prediction — mentioned by fulafel

Wed, 06 May 2026 12:30:57 GMT

Multi-token prediction is a refined form of speculative decoding. Researchers at Google came up with Speculative decoding in 2022: https://research.google/blog/looking-back-at-speculative-dec... (Fast Inference from Transformers via Speculative Decoding - Yaniv Leviathan, Matan Kalman, Yossi Matias) Researchers at Meta came up with MTP, a smarter way of doing speculative decoding in 2024: https://arxiv.org/abs/2404.19737 (Better & Faster Large Language Models via Multi-token Prediction Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve) DeepSeek V3…

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

Better & Faster Large Language Models via Multi-token Prediction — mentioned by fulafel

Wed, 06 May 2026 08:24:29 GMT

Looks like DeepSeek did this as well since V3: https://deepwiki.com/deepseek-ai/DeepSeek-V3/4.4-multi-token... Credit for the MTP technique is due to https://arxiv.org/abs/2404.19737 from 2024: Better & Faster Large Language Models via Multi-token Prediction Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve

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

Better & Faster Large Language Models via Multi-token Prediction — mentioned by logickkk1

Tue, 05 May 2026 20:32:58 GMT

i think this is mixing two separate ideas. MTP is the training-side piece. speculative decoding is the inference trick. DeepSeek V3 used MTP as an auxiliary loss. the 2022 Google paper is speculative decoding. now Google is combining them. https://arxiv.org/abs/2404.19737

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

Better & Faster Large Language Models via Multi-token Prediction — mentioned by Tostino

Wed, 24 Jul 2024 22:23:02 GMT

I think the work on multi-token prediction[0] within a single turn could be a significant development that makes byte-level tokenization models more practical. This approach allows the model to predict multiple tokens in parallel, potentially addressing the efficiency concerns raised about byte-level models. By predicting multiple tokens simultaneously, it could significantly speed up inference time, especially for tasks that require generating large amounts of data (like images). This could help mitigate the performance bottleneck mentioned in the parent comment about generating a 1000x1000…

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

Better & Faster Large Language Models via Multi-token Prediction — mentioned by ljlolel

Wed, 01 May 2024 14:07:55 GMT

https://arxiv.org/pdf/2404.19737

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

Better & Faster Large Language Models via Multi-token Prediction — HN submission

Wed, 01 May 2024 08:28:18 GMT

Better and Faster Large Language Models via Multi-Token Prediction

302 points; 128 discussion replies on HN. Paper and source history. A submission is not an endorsement.