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.

Tabby v0.1.1: Metal inference and StarCoder supports

4 pointsby wsxiaoysover 1 year ago

1 comment

wsxiaoysover 1 year ago
Previously, Tabby ran exclusively on CUDA devices, posing a significant barrier for developers looking to effectively utilize LLMs in their day-to-day coding.<p>The Tabby team made a significant contribution by enhancing support for the StarCoder series models (1B&#x2F;3B&#x2F;7B) in llama.cpp. This enhancement allows these models to run on Metal, providing comparable performance to that of an NVIDIA GPU.