Use view() instead of rearrange() for better performance.

This commit is contained in:
Ryan Dick
2024-11-24 04:31:02 +00:00
parent bb098ec064
commit abdf2a7f86

View File

@@ -28,8 +28,8 @@ def rope(pos: Tensor, dim: int, theta: int) -> Tensor:
def apply_rope(xq: Tensor, xk: Tensor, freqs_cis: Tensor) -> tuple[Tensor, Tensor]:
xq_ = xq.float().reshape(*xq.shape[:-1], -1, 1, 2)
xk_ = xk.float().reshape(*xk.shape[:-1], -1, 1, 2)
xq_ = xq.view(*xq.shape[:-1], -1, 1, 2)
xk_ = xk.view(*xk.shape[:-1], -1, 1, 2)
xq_out = freqs_cis[..., 0] * xq_[..., 0] + freqs_cis[..., 1] * xq_[..., 1]
xk_out = freqs_cis[..., 0] * xk_[..., 0] + freqs_cis[..., 1] * xk_[..., 1]
return xq_out.reshape(*xq.shape).type_as(xq), xk_out.reshape(*xk.shape).type_as(xk)
return xq_out.view(*xq.shape).type_as(xq), xk_out.view(*xk.shape).type_as(xk)