Add Builds

build/torch27-cxx11-cu118-x86_64-linux/layer_norm/layers.py

@@ -10,7 +10,7 @@ class LayerNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,
@@ -33,7 +33,7 @@ class LlamaRMSNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,

build/torch27-cxx11-cu126-x86_64-linux/layer_norm/layers.py

@@ -10,7 +10,7 @@ class LayerNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,
@@ -33,7 +33,7 @@ class LlamaRMSNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,

build/torch27-cxx11-cu128-x86_64-linux/layer_norm/layers.py

@@ -10,7 +10,7 @@ class LayerNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,
@@ -33,7 +33,7 @@ class LlamaRMSNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,

build/torch28-cxx11-cu126-x86_64-linux/layer_norm/layers.py

@@ -10,7 +10,7 @@ class LayerNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,
@@ -33,7 +33,7 @@ class LlamaRMSNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,

build/torch28-cxx11-cu128-x86_64-linux/layer_norm/layers.py

@@ -10,7 +10,7 @@ class LayerNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,
@@ -33,7 +33,7 @@ class LlamaRMSNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,

build/torch28-cxx11-cu129-x86_64-linux/layer_norm/layers.py

@@ -10,7 +10,7 @@ class LayerNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,
@@ -33,7 +33,7 @@ class LlamaRMSNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,

torch-ext/layer_norm/layers.py

@@ -10,7 +10,7 @@ class LayerNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,
@@ -33,7 +33,7 @@ class LlamaRMSNorm(nn.Module):
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         output = ops.dropout_add_ln_fwd(
-            hidden_states.view(hidden_states.shape[0], -1),
+            hidden_states.view(-1, hidden_states.shape[-1]),
             gamma = self.weight,
             beta = None,
             rowscale = None,