人工智能2023 · 分享于 Hacker News
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
探索《LLM in a Flash: Efficient Large Language Model Inference with Limited Memory》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。
Yweirdcat ·
Ferret: A Multimodal Large Language Model
621 赞同308 评论
Yhomarp ·
Towards 1-bit Machine Learning Models
351 赞同157 评论
Ythunderbong ·
Apple wants AI to run directly on its hardware instead of in the cloud
235 赞同203 评论
YBAAIBeijing ·
Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model
153 赞同27 评论
Ytosh ·
Apple Closes in on Deal with OpenAI to Put ChatGPT on iPhone
62 赞同49 评论
Ysteveharing1 ·
Granite 4.1: IBM's 8B Model Matching 32B MoE
27 赞同5 评论
Yrntn ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
18 赞同1 评论
Ykeep_reading ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
12 赞同1 评论
Ym-hodges ·
Qwen3.5-397B at 4.74 tok/s using 5.9GB RAM
10 赞同0 评论
Yanemll ·
iPhone 17 Pro Demonstrated Running a 400B LLM
6 赞同5 评论
Yghshephard ·
Apple Announces LLM in a Flash: Efficient LLM Inference with Limited Memory
5 赞同1 评论
Yrobin_reala ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
5 赞同0 评论
Yinterpol_p ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
3 赞同0 评论
Ysherlockxu ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
3 赞同1 评论
YPaulHoule ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
3 赞同0 评论
Ysaikatsg ·
LLM in a Flash
2 赞同0 评论
Yabhinavk ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
2 赞同0 评论
Ympweiher ·
LLM in a Flash: Efficient Large Language Model Inference with Limited Memory
1 赞同0 评论
Y_ktnd ·
Ask HN: How to execute an 180B+ LLM on a Turing machine?
1 赞同0 评论