Skip to content
Hot storiesContinuously updated

开发者开源 lowvram 显存优化工具

1 reports1 reporting sourcesUpdated 5 hours ago

Start here

AI overview

2026年11月6日，开发者开源了一款名为 lowvram 的命令行（CLI）显存优化工具。该工具的核心原理是通过拦截底层 CUDA 调用，将显存分配函数 cuMemAlloc 自动替换为托管内存（managed memory），使消费级低显存 GPU 无需修改任何源代码即可直接运行大型语言模型，降低了在消费级硬件上部署大模型的门槛。

AI-generated from reports · Updated 4 hours ago

Latest developmentsNov 6 20:29
开发者开源 CLI 工具 lowvram，通过拦截 CUDA 调用支持低显存 GPU 运行大模型。

Report timeline

Follow the reports to see different sides of the story.

Nov 6
  1. Hacker News · AISelected
    CLI tool lowvram released: Running LLMs on low-VRAM GPUs via CUDA memory interception

    Developers have open-sourced lowvram, a CLI tool that intercepts low-level CUDA calls to replace cuMemAlloc with managed memory, enabling consumer low-VRAM GPUs to run large language models without source code modifications.

Story heat trend

Current heat 9·Comparable peak 10（Nov 6 22:00）·Comparable change, last 24 hours–

02.557.510Nov6Nov6Nov7Nov7

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.