Zhihan Fang db5970c1a6 [coreml-backend-tool] fix pytorch-backended issue on new coremltools (#155543) ... Summary: the new coreml tool is export mlpakage instead mlmodel in default option. when we use new 8.0 coreml tool to convert to backend, the error is ``` Exception: MLModel of type mlProgram cannot be loaded just from the model spec object. It also needs the path to the weights file. Please provide that as well, using the 'weights_dir' argument. ``` Test Plan: tested with internal workflow Rollback Plan: Differential Revision: D76325462 Pull Request resolved: https://github.com/pytorch/pytorch/pull/155543 Approved by: https://github.com/shoumikhin		2025-06-11 20:52:26 +00:00
..
_coreml	[coreml-backend-tool] fix pytorch-backended issue on new coremltools (#155543)	2025-06-11 20:52:26 +00:00
_nnapi
cpu
cuda	Revert "refine fp32 precision api (#125888)"	2025-05-11 00:35:46 +00:00
cudnn	Revert "refine fp32 precision api (#125888)"	2025-05-11 00:35:46 +00:00
cusparselt
kleidiai
mha
mkl
mkldnn	Revert "refine fp32 precision api (#125888)"	2025-05-11 00:35:46 +00:00
mps
nnpack
openmp
opt_einsum
quantized	PEP585: More UP006 fixes (#146392)	2025-02-20 06:18:13 +00:00
xeon
xnnpack
__init__.py	Revert "refine fp32 precision api (#125888)"	2025-05-11 00:35:46 +00:00