Photon 2.2 Ships Optimized Local Inference for Ampere Through Blackwell GPUs

JFPuget · x · 2026-09-10

vikhyatk announces Photon 2.2, adding optimized local inference across NVIDIA Ampere, Ada, Hopper, and Blackwell GPUs — including A10/A10G, A100, RTX 3090, L4, H100, B200, and RTX PRO 6000 Blackwell.

Original post →

More from Infra

Infra channel →