Jason Ansel b040dc3a53 Reland: [inductor] Simplify grid handling (#148305) ... Summary: Relands D69965761 / https://github.com/pytorch/pytorch/pull/147583 Before this PR, calling a triton kernel would look like: ```py kernel.run(a, b, xnumel, grid=grid(xnumel), stream=stream0) ``` where the `grid=` was passed as a callable (function closure) arg. This PR removes the grid arg: ```py kernel.run(a, b, xnumel, stream=stream0) ``` instead now the grid computation is included in the kernel launcher, with something like: ```py def launcher(in_ptr0, out_ptr0, xnumel, stream): grid_0 = ((xnumel + 1023) >> 10) grid_1 = 1 grid_2 = 1 runner(grid_0, grid_1, grid_2, stream, function, metadata, None, launch_enter_hook, launch_exit_hook, in_ptr0, out_ptr0, xnumel) ``` This should be faster, since we remove multiple function/dict calls and are able to specialize the grid computation for each `triton.Config`. It also allows us to unify the handling of grids between the Python and C++ wrapper code. Before this, C++ wrapper code didn't actually support dynamic grid sizes and instead burned in a static grid. This unification allows this PR to be a net deletion of code. Differential [disconnected] Revision: D70471332 Pull Request resolved: https://github.com/pytorch/pytorch/pull/148305 Approved by: https://github.com/shunting314, https://github.com/eellison		2025-03-12 15:52:16 +00:00
..
__init__.py
device_op_overrides.py	Reland: [inductor] Simplify grid handling (#148305)	2025-03-12 15:52:16 +00:00