Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
C
Commits on main
gpu_unlock: decode PMCSR D0 with a helper
ca78f02 randomizedcoder [email protected] committed 22 days ago
gpu_unlock: take gfp_t in diag_dma_alloc()
500e48c randomizedcoder [email protected] committed 22 days ago
Merge pull request #162 from viwe-monai/docs-tested-cards-reports
5721707 Simon committed 24 days ago
Merge pull request #140 from lemonaide152/readme-tested-3070-lhr
c50982d Simon committed 24 days ago
docs: add RTX 3090 reports #148, #152, #155, #158 to the tested cards table
2e4af94 viwe-monai committed 24 days ago
README: add RTX 3070 LHR (10de:2488) to the tested cards table
e9f9408 lemonaide152 committed 25 days ago
Merge pull request #37 from tsondo/claude/wizardly-turing-ecpa8w
af28cbb Simon committed 26 days ago
Merge pull request #39 from tsondo/claude/wizardly-turing-ecpa8w-issue-template
727561f Simon committed 26 days ago
Merge pull request #40 from tsondo/claude/wizardly-turing-ecpa8w-supported-cards
5f30eaa Simon committed 26 days ago