Hongxin Liu d202cc28c0 [npu] change device to accelerator api (#5239) ... * update accelerator * fix timer * fix amp * update * fix * update bug * add error raise * fix autocast * fix set device * remove doc accelerator * update doc * update doc * update doc * use nullcontext * update cpu * update null context * change time limit for example * udpate * update * update * update * [npu] polish accelerator code --------- Co-authored-by: Xuanlei Zhao <xuanlei.zhao@gmail.com> Co-authored-by: zxl <43881818+oahzxl@users.noreply.github.com>		2024-01-09 10:20:05 +08:00
..
cuda_native	[npu] use extension for op builder (#5172)	2024-01-08 11:39:16 +08:00
extensions	[npu] change device to accelerator api (#5239)	2024-01-09 10:20:05 +08:00
jit	[npu] change device to accelerator api (#5239)	2024-01-09 10:20:05 +08:00
triton	[Kernels]added flash-decoidng of triton (#5063)	2023-11-20 13:58:29 +08:00
__init__.py	[npu] use extension for op builder (#5172)	2024-01-08 11:39:16 +08:00
base_kernel_loader.py	[npu] use extension for op builder (#5172)	2024-01-08 11:39:16 +08:00
cpu_adam_loader.py	[npu] use extension for op builder (#5172)	2024-01-08 11:39:16 +08:00
flash_attention_loader.py	[npu] use extension for op builder (#5172)	2024-01-08 11:39:16 +08:00
op_builder	[builder] reconfig op_builder for pypi install (#2314)	2023-01-04 16:32:32 +08:00