Oguz Ulgen 79ee6bbde3 Support triton.language.dtype with torch.compile (#121690) ... Putting this PR as an RFC since I have resorted to some horrible hacks in order to make this work. ``` (Pdb) p triton.language.float32 triton.language.fp32 (Pdb) p str(triton.language.float32) 'fp32' (Pdb) p repr(triton.language.float32) 'triton.language.fp32' ``` This means that we need to "rewrite" them for fx graph and inductor execution. This PR allows Mamba2 to work with `torch.compile`. Pull Request resolved: https://github.com/pytorch/pytorch/pull/121690 Approved by: https://github.com/Skylion007		2024-03-12 23:21:46 +00:00
..
aoti_runtime	[Inductor] Enable ABI-compatible mode for cpp-wrapper JIT (#121309)	2024-03-07 14:22:06 +00:00
cuda	Revert "Add CUTLASS kernel as choice for _int_mm() Inductor autotuning (#119685)"	2024-03-09 07:20:53 +00:00
__init__.py
common.py	[inductor] Changes to support newer triton pin (#121267)	2024-03-09 18:17:36 +00:00
cpp_prefix.h	Revert "[Inductor] Add support for NEON ISA in the Inductor C++ backend (#105590)"	2024-03-07 23:06:29 +00:00
cpp_wrapper_cpu.py	Change assertion throw to error message for const_run_impl call. (#121396)	2024-03-08 22:48:43 +00:00
cpp_wrapper_cuda.py	Add torch.cond support to AOT Inductor (#121120)	2024-03-07 22:39:57 +00:00
cpp.py	[Quant][Inductor] Fix q/dq per channel lowering with 64-bit qparams (#120984)	2024-03-07 06:23:52 +00:00
cuda_combined_scheduling.py	[mypy] added type annotations to codegen_nodes methods (#119080)	2024-02-05 18:33:52 +00:00
memory_planning.py	Remove follow_imports = skip from sympy (#118469)	2024-01-28 13:38:38 +00:00
multi_kernel.py	[inductor] make multi-kernel work with cpp-wrapper (#117813)	2024-02-05 23:35:41 +00:00
triton_foreach.py	[inductor] Refactor common triton imports into one function (#121438)	2024-03-09 18:17:36 +00:00
triton_split_scan.py	[inductor] Add split scan kernel (#117992)	2024-02-09 01:56:00 +00:00
triton_utils.py	Add equal_to_1 to triton_meta for user-written Triton kernels (#120579)	2024-02-29 05:19:39 +00:00
triton.py	Express y grid > 2^16 in terms of z grid (#121554)	2024-03-12 02:36:19 +00:00
wrapper.py	Support triton.language.dtype with torch.compile (#121690)	2024-03-12 23:21:46 +00:00