5 Commits

Author	SHA1	Message	Date
Sherlock Huang	fb067de550	[NativeRT] Remove device_ member from OpKernel base class (#158944) ... Summary: In general, device_ is not very useful in OpKernel. Remove it to avoid misuse. Also, the meaning of `device_` is also ambiguous in the OpKernel. For StaticDispatch kernels, we always call cpu kernel. For C10Kernel, we rely on input tensor's device and dispatcher to determine which device to run on. For ops involves multiple device, e.g. aten._to_copy(device), the meaning of device is ill-defined. Test Plan: CI Rollback Plan: Reviewed By: henryoier, dolpm, kqfu, zhxchen17 Differential Revision: D78704840 Pull Request resolved: https://github.com/pytorch/pytorch/pull/158944 Approved by: https://github.com/dolpm	2025-07-24 09:21:37 +00:00
Sherlock Huang	86dbc0ef67	[NativeRT] Remove makeProxyExecutor from ModelRunner interface (#158587) ... Summary: makeProxyExecutor shouldn't be exposed to ModelRunner Interface. Test Plan: CI Rollback Plan: Differential Revision: D78501011 Pull Request resolved: https://github.com/pytorch/pytorch/pull/158587 Approved by: https://github.com/yiming0416, https://github.com/henryoier	2025-07-18 03:20:40 +00:00
dolpm	144965ca9a	[BE][S538760] get rid of TORCH_CHECK_.* and CHECK macros (#158269) ... Summary: check will be crit, causing program to exit, which is quite dangerous Test Plan: CI Rollback Plan: Differential Revision: D78050595 Pull Request resolved: https://github.com/pytorch/pytorch/pull/158269 Approved by: https://github.com/SherlockNoMad, https://github.com/henryoier	2025-07-15 22:04:12 +00:00
dolpm	725c327284	[nativert] add memory overlap debug assertion (#157290) ... Summary: better safe than sorry. will throw if memory overlap detected when using planned tensors and debug mode is enabled -- this will make our planning unit tests more robust. Test Plan: ci Rollback Plan: Differential Revision: D77327841 Pull Request resolved: https://github.com/pytorch/pytorch/pull/157290 Approved by: https://github.com/SherlockNoMad, https://github.com/zhxchen17	2025-07-14 19:12:41 +00:00
Sheng Qin	88c6199db0	[nativert] Move KernelFactory to PyTorch core (#156913) ... Summary: Kernel factory handles the kernel nodes initializations and different type of kernels executions. Test Plan: CI Rollback Plan: Differential Revision: D77346836 Pull Request resolved: https://github.com/pytorch/pytorch/pull/156913 Approved by: https://github.com/zhxchen17	2025-06-28 06:34:24 +00:00