人工智能2023 · 分享于 Hacker News
Accelerating Large Language Model Decoding with Speculative Sampling
探索《Accelerating Large Language Model Decoding with Speculative Sampling》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Yfigomore ·
AMD Unveils Its First Small Language Model AMD-135M
311 赞同97 评论
Yjasondavies ·
Better and Faster Large Language Models via Multi-Token Prediction
302 赞同128 评论
Ysrameshc ·
Run 100B+ language models at home, BitTorrent‑style
91 赞同19 评论
Ydavidbarker ·
Stability AI Launches the First of Its StableLM Suite of Language Models
76 赞同15 评论
Yamrrs ·
Accelerating Gemma 4: faster inference with multi-token prediction drafters
36 赞同7 评论
Yd99kris ·
Major Outage Across ChatGPT and API
24 赞同8 评论
Ymicro_charm ·
Facebook LLAMA is being openly distributed via torrents
4 赞同1 评论
Ymrtksn ·
LLaMA-7B in Pure C++ with full Apple Silicon support
2 赞同1 评论
Ygeorgehill ·
Accelerating Large Language Model Decoding with Speculative Sampling
1 赞同0 评论
Ytim_sw ·
(Databricks cofounder) How Is ChatGPT’s Behavior Changing over Time?
1 赞同0 评论
YJimmc414 ·
Accelerating Large Language Model Decoding with Speculative Sampling
1 赞同0 评论