Commit Graph

6 Commits

Author SHA1 Message Date
Ethan Yang
e14b8dfec5
Update nodes_torch_compile.py 2025-03-07 13:23:19 +08:00
ethan
bc9eb9dfdb fix the memory leakage issue 2025-03-05 18:28:47 -08:00
ethan
77e9294c08 add Query Device 2025-01-30 00:20:58 -08:00
ethan
d1f61cca5e add openvino to torch compile 2025-01-29 07:03:31 -08:00
comfyanonymous
83b01f960a Add backend option to TorchCompileModel.
If you want to use the cudagraphs backend you need to: --disable-cuda-malloc

If you get other backends working feel free to make a PR to add them.
2024-09-27 02:12:37 -04:00
comfyanonymous
d0b7ab88ba Add a simple experimental TorchCompileModel node.
It probably only works on Linux.

For maximum speed on Flux with Nvidia 40 series/ada and newer try using
this node with fp8_e4m3fn and the --fast argument.
2024-09-12 05:24:25 -04:00