PulseAugur
中
实时 03:28:34
English(EN) Janas: Run LLMs larger than RAM by streaming experts from SSD https:// github.com/prabanta-dev/janas Comments: https:// news.ycombinator.com/item?id=5 0063717 #

Janas 项目通过 SSD 流式传输实现大于 RAM 的 LLM 运行

一个名为 Janas 的新开源项目,通过高效地从固态硬盘 (SSD) 流式传输模型层,实现了运行超出计算机可用 RAM 的大型语言模型 (LLM)。这项技术使得在消费级硬件上运行比以往更大的模型成为可能。该项目的代码可在 GitHub 上获取。 AI

影响 通过 SSD 流式传输优化内存管理,从而在消费级硬件上运行更大的 LLM。

排序理由 开源项目发布,详细介绍了一种运行大型模型的新技术。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Janas 项目通过 SSD 流式传输实现大于 RAM 的 LLM 运行

本文如何被排名

Signal score
10 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
开源项目发布,详细介绍了一种运行大型模型的新技术。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · h4ckernews ·

    Janas:通过从 SSD 流式传输专家来运行大于 RAM 的 LLM https:// github.com/prabanta-dev/janas Comments: https:// news.ycombinator.com/item?id=5 0063717 #

    Janas: Run LLMs larger than RAM by streaming experts from SSD https:// github.com/prabanta-dev/janas Comments: https:// news.ycombinator.com/item?id=5 0063717 # HackerNews # Janas # LLMs # SSD # Streaming # AI # Technology # MachineLearning