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
Merge pull request #160 from nklowns/add-ga106m-2560
Simon990a14e9b7dc
diff --cc README.mdindex 39e2a8d,da010cb..ae48fa0--- a/README.md+++ b/README.md@@@ -33,9 -33,9 +33,10 @@@ whether it worked or not| GA102 | RTX 3080 10 GB | `10de:2206` | Unlocked | +70–73% | [#14](https://github.com/Zagitta/gpu-unlock/issues/14) || GA102 | RTX 3080 20 GB (memory upgrade) | `10de:2206` | Unlocked | +56–59% | [#10](https://github.com/Zagitta/gpu-unlock/issues/10), [#15](https://github.com/Zagitta/gpu-unlock/issues/15) || GA104 | RTX 3070 | `10de:2484` | Unlocked | +73–81% | [#10](https://github.com/Zagitta/gpu-unlock/issues/10), [#12](https://github.com/Zagitta/gpu-unlock/issues/12) |+| GA104 | RTX 3070 LHR | `10de:2488` | Unlocked | +77–84% | [#74](https://github.com/Zagitta/gpu-unlock/issues/74), [#137](https://github.com/Zagitta/gpu-unlock/issues/137) || GA104 | RTX 3070 Ti | `10de:2482` | Not tested with this module (the same unlock worked from a UEFI port on Windows) | — | [#32](https://github.com/Zagitta/gpu-unlock/issues/32) || GA106 | RTX 3060 12 GB | `10de:2504` | Unlocked | about +80% | [#13](https://github.com/Zagitta/gpu-unlock/pull/13), [#31](https://github.com/Zagitta/gpu-unlock/issues/31) |+ | GA106M | RTX 3060 Laptop 6 GB | `10de:2560` | Unlocked | +56–60% | [#86](https://github.com/Zagitta/gpu-unlock/issues/86) || GA103 | any | `10de:2414` | No reports yet | — | — |The gains are dense GEMM throughput from each report's own benchmark, so