Full nvfp4 training for GeForce RTX 50-series and RTX PRO 6000 Blackwell GPUs with Infatoshi/nvfp4-sm120 on SM120; six profiles for speed and memory
Read the original at github.com→★ 80 stars
Original headline: "xl03-bit/sm120-nvfp4-training: Full NVFP4 training for GeForce RTX 50-series and RTX PRO 6000 Blackwell GPUs (SM120). Built on Infatoshi/nvfp4-sm120, with software stochastic rounding, random Hadamard transforms and six profiles for speed and memory. On one RTX 5060 Ti 16GB, validation loss fell ove"
Coverage timeline
- Nov 2, 07:39 UTC GitHub Trending (AI) lead source xl03-bit/sm120-nvfp4-training: Full NVFP4 training for GeForce RTX 50-series and RTX PRO 6000 Blackwell GPUs (SM120). Built on Infatoshi/nvfp4-sm120, with software stochastic rounding, random Hadamard transforms and six profiles for speed and memory. On one RTX 5060 Ti 16GB, validation loss fell ove