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 05:23:32 -04:00
parent 405b529545
commit d0b7ab88ba
2 changed files with 22 additions and 0 deletions
--- a/nodes.py
+++ b/nodes.py
@@ -2102,6 +2102,7 @@ def init_builtin_extra_nodes():
        "nodes_hunyuan.py",
        "nodes_flux.py",
        "nodes_lora_extract.py",
+        "nodes_torch_compile.py",
    ]

    import_failed = []