2026-11-05 · America/Los_Angeles · 社区动态 · #4
Quantization livestream with goats of inference
Hey folks, it's Merve from Hugging Face. Title of this post is super self explanatory, we are doing a quantization workshop livestream with Michael Goin (lead maintainer of vLLM at RedHat), Colin Kealty (aka bartowski at RedHat), Maxime Labonne and Aditya Tadimeti. I will shortly teach you how quantization works, modern ideas (double quantization, calibration) and llama.cpp quants (k-quants, i-quants) so even if you don't have an idea, feel free to chime in. Everything is on Hugging Face YT, X, LI where you can set reminders. Looking forward to see y'all!
热度 41.3 / 100;排名与评分保留该期记录。