Open Source3h ago

Detected, not submitted

llama.cpp

Own llama.cpp?

Verify your site to claim this listing and get emailed the moment a buyer's looking for something like it.

This is mine — claim it
llama.cpp preview

A fork of llama.cpp that achieves 2-4x faster multiGPU speed for Mixture of Experts models that exceed individual VRAM capacity

Spotted on Hacker News on September 25, 2026.

NE

neuralll

Maker