Nikita Shulga 3aecf2dc52 [MPS] Extend index_put to half precision floats (#151869) ... By reusing `c10/metal/atomic.h` This also fixes `GPUTests.test_index_put_fallback[12]_mps` that is unrolled by inductor, so no need for dedicated atomic_add support TODOs: - Get rid of indexing kernel and compute it directly when kernel is run - Simulate atomic_add for int64 types as series of int32 atomic-add-and-fetch - Setup tolerances correctly to pass float16/bfloat16 tests (as CPU always takes sequential strategy) Pull Request resolved: https://github.com/pytorch/pytorch/pull/151869 Approved by: https://github.com/Skylion007, https://github.com/dcci		2025-04-22 22:00:08 +00:00
..
_internal	[MPS] Extend index_put to half precision floats (#151869)	2025-04-22 22:00:08 +00:00
__init__.py	[BE][Easy][19/19] enforce style for empty lines in import segments in torch/[o-z]*/ (#129771)	2024-08-01 17:07:14 +00:00
_comparison.py	Support fp8 dtypes in assert_close (#150002)	2025-04-20 01:24:21 +00:00
_creation.py	PEP585 update - torch/testing (#145200)	2025-01-20 22:42:42 +00:00
_utils.py	Fix code descriptions in the test package. (#148145)	2025-03-04 19:14:41 +00:00