tensor: add narrow() view and relax is_contiguous for size-1 dims

narrow(dim, start, len) creates a zero-copy slice along any dimension.
is_contiguous() now ignores stride mismatches on dimensions of size 1,
since those dimensions are never stepped. This avoids unnecessary GPU
strided copies when slicing fused projection outputs at batch=1.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/xserv-tensor/src/tensor.rs

@@ -120,6 +120,21 @@ impl Tensor {
         }
     }
 
+    /// Zero-copy slice along `dim`: keeps elements `[start, start+len)`.
+    pub fn narrow(&self, dim: usize, start: usize, len: usize) -> Self {
+        assert!(dim < self.ndim());
+        assert!(start + len <= self.shape[dim], "narrow out of bounds");
+        let mut new_shape = self.shape.clone();
+        new_shape[dim] = len;
+        Self {
+            storage: self.storage.clone(),
+            shape: new_shape,
+            strides: self.strides.clone(),
+            offset: self.offset + start * self.strides[dim],
+            dtype: self.dtype,
+        }
+    }
+
     pub fn transpose(&self, dim0: usize, dim1: usize) -> Self {
         assert!(dim0 < self.ndim() && dim1 < self.ndim());
         let mut new_shape = self.shape.clone();