insidentally.com

在 Fedora 44 上编译支持 CUDA 的 llama.cpp:完整指南 (opens in new tab)

llama.cpp 是本地运行大模型的首选推理引擎,但官方预编译版本在 Linux 上不提供 CUDA 支持。本文记录了在 Fedora 44 系统上,使用 Toolbox 容器从源码编译支持 CUDA 13.2 的 llama.cpp 的完整过程,包括环境配置、依赖解决和性能优化。

Read the original article
Sign in to keep reading the full article.

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help