pytorch/torch/_inductor/codegen
Bin Bao ee1dbb2acf [AOTI] Fix a None as index codegen issue (#118187)
Summary: Fix a ABI-compatible codegen issue when index_put has None in its indices.

Differential Revision: [D53047489](https://our.internmc.facebook.com/intern/diff/D53047489)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/118187
Approved by: https://github.com/chenyang78
ghstack dependencies: #118168, #118169
2024-01-25 11:53:44 +00:00
..
aoti_runtime [AOTInductor] Allow user to explicitly specify Device to run on (#117413) 2024-01-17 19:28:04 +00:00
cuda [BE]: Enable F821 and fix bugs (#116579) 2024-01-01 08:40:46 +00:00
__init__.py
common.py Rename unbacked SymInt prefix to u (#117859) 2024-01-22 20:53:47 +00:00
cpp_prefix.h add mask_convert_to_lp to support bool->fp16/bf16 convert (#117830) 2024-01-23 07:52:43 +00:00
cpp.py add mask_convert_to_lp to support bool->fp16/bf16 convert (#117830) 2024-01-23 07:52:43 +00:00
cuda_combined_scheduling.py [Inductor CUTLASS backend] Epilogue fusion codegen (Step 1) (#110890) 2023-11-06 19:42:10 +00:00
memory_planning.py Properly type CachedFunction & rename to CachedMethod (#114161) 2023-11-25 01:30:23 +00:00
multi_kernel.py [inductor] multi-kernel support (#103469) 2024-01-18 23:16:31 +00:00
triton_foreach.py [inductor] make inductor work with new triton compile interface (#115878) 2023-12-22 00:09:29 +00:00
triton_utils.py additional support for float8_e4m3fnuz and _e5m2fnuz (#115214) 2024-01-22 18:33:41 +00:00
triton.py Rename unbacked SymInt prefix to u (#117859) 2024-01-22 20:53:47 +00:00
wrapper.py [AOTI] Fix a None as index codegen issue (#118187) 2024-01-25 11:53:44 +00:00