Manning prints 'CUDA for LLMs,' a 408-page guide to fast transformer kernels, 50% off till Dec 4

eigenron · x · 2026-11-18

Elliot Arledge's book 'CUDA for LLMs' (formerly early-access 'CUDA for Deep Learning') is now in print via Manning: 408 pages on building fast transformer kernels, with source code on GitHub, chapter briefs, forums, and a Simplified Chinese edition. Code PBArledge gives 50% off all formats through Dec 4 (eBook $27.99, print+eBook $34.99).

Original post →

More from Infra

Infra channel →