TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Llama.go – port of llama.cpp to pure Go

25 pointsby Ambixabout 2 years ago
It&#x27;s April 12 - The First Man in Space* Day - and I&#x27;m releasing #ML framework I&#x27;ve been building for the last month :)<p>It&#x27;s written in #Go and allows #LLaMA #GPT inference having just regular PC - so no monster GPU cluster is needed to start experiment with:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;gotzmann&#x2F;llama.go">https:&#x2F;&#x2F;github.com&#x2F;gotzmann&#x2F;llama.go</a><p>The V1 is using FP32 math only, but will work with AVX2 data types and INT8 quantisation soon.<p>* The first man in space was Yuri Gagarin from USSR

3 comments

ipaddrabout 2 years ago
Do we have a php version yet
smcleodabout 2 years ago
&quot;Pure Go&quot; ... looks at repo - 16.9% python.
评论 #35554882 未加载
评论 #35578832 未加载
toughabout 2 years ago
very cool, waiting for llama.rust any day now