Repo

speedlm

by Ryan Kim · Sophont

Automatically speeds up supported local LLM profiles with idle GPU time—keeping data local and the OpenAI-compatible serving workflow.

Built with

Pythoncudadeveloper-toolsllm-inferencemachine-learning

pytorch

Comments · 0

No comments yet. Tried it? Tell Ryan what worked, what didn't, or what you'd want next.

See what other members are building and what each project is looking for.