diff --git a/activation/flake.lock b/activation/flake.lock
index 1413b98e..5603c235 100644
--- a/activation/flake.lock
+++ b/activation/flake.lock
@@ -41,16 +41,15 @@
         "rust-overlay": "rust-overlay"
       },
       "locked": {
-        "lastModified": 1777901020,
-        "narHash": "sha256-m54hEdh1kK+pDcRfJDwN0P861X5VWpC/yZ1TjTwshtA=",
+        "lastModified": 1779099126,
+        "narHash": "sha256-pjHUA4mQ+Opm04nBTetc6+rEFSwtkL49e1nAy1APLcM=",
         "owner": "huggingface",
         "repo": "kernels",
-        "rev": "614c6bb2ee922a832852cb5562d5571cd9600a9c",
+        "rev": "f4cc83f0301c59f3647663d45357b76e3468244a",
         "type": "github"
       },
       "original": {
         "owner": "huggingface",
-        "ref": "torch-2.12",
         "repo": "kernels",
         "type": "github"
       }
diff --git a/activation/flake.nix b/activation/flake.nix
index 5186161b..f8ee7ca9 100644
--- a/activation/flake.nix
+++ b/activation/flake.nix
@@ -2,7 +2,7 @@
   description = "Flake for activation kernels";
 
   inputs = {
-    kernel-builder.url = "github:huggingface/kernels/torch-2.12";
+    kernel-builder.url = "github:huggingface/kernels";
   };
 
   outputs =
diff --git a/activation/torch-ext/activation/__init__.py b/activation/torch-ext/activation/__init__.py
index 1a9cd15a..cfce59ba 100644
--- a/activation/torch-ext/activation/__init__.py
+++ b/activation/torch-ext/activation/__init__.py
@@ -5,56 +5,56 @@
 from . import layers
 
 
-def silu_and_mul(out: torch.Tensor, x: torch.Tensor) -> None:
+def silu_and_mul(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.silu_and_mul(out, x)
     return out
 
 
-def mul_and_silu(out: torch.Tensor, x: torch.Tensor) -> None:
+def mul_and_silu(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.mul_and_silu(out, x)
     return out
 
 
-def gelu_and_mul(out: torch.Tensor, x: torch.Tensor) -> None:
+def gelu_and_mul(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.gelu_and_mul(out, x)
     return out
 
 
-def gelu_tanh_and_mul(out: torch.Tensor, x: torch.Tensor) -> None:
+def gelu_tanh_and_mul(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.gelu_tanh_and_mul(out, x)
     return out
 
 
-def fatrelu_and_mul(out: torch.Tensor, x: torch.Tensor, threshold: float = 0.0) -> None:
+def fatrelu_and_mul(out: torch.Tensor, x: torch.Tensor, threshold: float = 0.0) -> torch.Tensor:
     ops.fatrelu_and_mul(out, x, threshold)
     return out
 
 
-def gelu(out: torch.Tensor, x: torch.Tensor) -> None:
+def gelu(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.gelu(out, x)
     return out
 
-def silu(out: torch.Tensor, x: torch.Tensor) -> None:
+def silu(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.silu(out, x)
     return out
 
 
-def gelu_tanh(out: torch.Tensor, x: torch.Tensor) -> None:
+def gelu_tanh(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.gelu_tanh(out, x)
     return out
 
 
-def gelu_fast(out: torch.Tensor, x: torch.Tensor) -> None:
+def gelu_fast(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.gelu_fast(out, x)
     return out
 
 
-def gelu_new(out: torch.Tensor, x: torch.Tensor) -> None:
+def gelu_new(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.gelu_new(out, x)
     return out
 
 
-def gelu_quick(out: torch.Tensor, x: torch.Tensor) -> None:
+def gelu_quick(out: torch.Tensor, x: torch.Tensor) -> torch.Tensor:
     ops.gelu_quick(out, x)
     return out