enable OffloadedCache on XPU from PyTorch 2.7 (#36654)
* fix "Cannot copy out of meta tensor; no data!" issue for BartForConditionalGeneration model
* follow Marc's suggestion to use _tie_weights to fix
Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
* enable OffloadedCache on XPU since PyTorch 2.7
Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
* fix style
Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
* don't change bart
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com>
* make code more concise per review comments
Signed-off-by: N <matrix.yao@intel.com>
* fix review comments
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com>
* Revert "fix review comments"
This reverts commit acf1484b86c7cc58b2dee69e7008c0eeb4c97b1b.
* fix review comments
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com>
* fix style
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com>
---------
Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com>
Signed-off-by: N <matrix.yao@intel.com>
Co-authored-by: root <root@a4bf01945cfe.jf.intel.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
