GitHub Today's Pick | gpu-unlock-ada: Double the Tensor Compute Power of Ada GPUs with Unlock
By modifying hardware registers via kernel modules before NVIDIA driver loading, FP16/BF16 tensor compute power for Ada GPUs like the RTX 4090 is doubled, rising from 165 TF/s to 331 TF/s.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open original at Juejin