QVAC(@qvac):Our third llama.cpp PR in a week has been merged. This one, by @gianniCor, fixes llama.cpp's Vulkan backend, where choosing the next token could freeze an NVIDIA GPU. Thanks to @ggml

QVAC

@qvac

Infinite intelligence. Local. Any Hardware. Peer-to-Peer Hyper Swarm. No cloud. No compromise. QVAC is the decentralized AI platform for humans and machines.

参加 April 2025

2 フォロー中 13.5K ファン

QVAC@qvac

2026.10.09 10:38

Our third llama.cpp PR in a week has been merged. This one, by @gianniCor, fixes llama.cpp's Vulkan backend, where choosing the next token could freeze an NVIDIA GPU. Thanks to @ggml_org for the review.