[Hardware][Intel GPU] Add Intel GPU(XPU) inference backend (#3814)

Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com>
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
This commit is contained in:
Kunshang Ji
2024-06-17 11:01:25 -07:00
committed by GitHub
co-authored by Jiang Li Abhilash Majumder Abhilash Majumder
parent 1f12122b17
commit 728c4c8a06
31 changed files with 1998 additions and 24 deletions
+1 -1
View File
@@ -58,7 +58,7 @@ def _split_tensor_dict(
# because it contains not only the device type but also the device
# index (e.g. "cuda:0"). We only need the device type.
# receiving side will set the device index.
device = "cpu" if value.is_cpu else "cuda"
device = value.device.type
metadata_list.append(
(key, TensorMetadata(device, value.dtype, value.size())))
tensor_list.append(value)