A two‑line change routes Volta (sm_70) to Turing’s MMVQ table, giving about a 3% speed gain on a Tesla V100 while keeping results identical.
NoteBy OossaPublished by Oossa: 1 min read
The llama.cpp project released a small CUDA update on 2026-10-02. It makes Volta GPUs (sm_70) use the same MMVQ tuning table as Turing GPUs. On a Tesla V100 32 GB the change added roughly 3 % throughput for the Qwen3.8‑27B model. The output quality, measured by perplexity, stayed the same. The patch was contributed by anyei and co‑authors.
Users running llama.cpp on V100 GPUs can run models slightly faster without losing accuracy.
Models
YouTube Music will mark tracks that use generative AI with “Fully Gen AI,” “Partly Gen AI,” or “No Gen AI” labels, starting Oct 14 2026.
Models
The new Probabilistic Bias Correction method can run on CPUs and boosts accuracy of existing models, helping farmers and emergency responders plan ahead.
Models
The Argon model is now in the Gemini app for Pro and Ultra subscribers, adding a tasks mode that works while you’re away.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
