We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent ab3163b commit cfe2582Copy full SHA for cfe2582
content/blog/2025-08-25-1756113601.md
@@ -44,13 +44,13 @@ For 10k iterations:
44
| Time | Framework | Environment |
45
| --- | --- | --- |
46
| 1.6s | plain torch | Ubuntu Linux (WSL) |
47
-| 1.9s | plain torch | Windows |
48
-| 2.6s | torch.compile() with Triton | Ubuntu Linux (WSL) |
49
-| 1.7s | TensorRT RTX | Windows |
50
| 1.6s | TensorRT | Windows |
51
| 1.6s | fused CUDA kernel | Windows |
52
-| 5.1s | fused Vulkan shader | Windows |
+| 1.7s | TensorRT RTX | Windows |
+| 1.9s | plain torch | Windows |
53
| 2.3s | ggml + CUDA | Windows |
+| 2.6s | torch.compile() with Triton | Ubuntu Linux (WSL) |
+| 5.1s | fused Vulkan shader | Windows |
54
| 5.3s | ggml + Vulkan | Windows |
55
56
0 commit comments