From 8fc9bc5ddaa07d00487ebdac8552afea6318e5f4 Mon Sep 17 00:00:00 2001 From: Fung Xie Date: Tue, 25 Nov 2025 21:26:00 -0800 Subject: [PATCH] update doc --- .../cute_dsl_general/compile_with_tvm_ffi.rst | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/media/docs/pythonDSL/cute_dsl_general/compile_with_tvm_ffi.rst b/media/docs/pythonDSL/cute_dsl_general/compile_with_tvm_ffi.rst index deb6229d1..dd6a934c8 100644 --- a/media/docs/pythonDSL/cute_dsl_general/compile_with_tvm_ffi.rst +++ b/media/docs/pythonDSL/cute_dsl_general/compile_with_tvm_ffi.rst @@ -351,18 +351,6 @@ The TVM FFI function supports the following |DSL|-specific types as arguments: - Python tuple of corresponding call-time types. -Note on Stride Order -~~~~~~~~~~~~~~~~~~~~ - -Note that cute's convention is to write the stride order for dimensions from left to right, -where a lower order number means higher priority. -For shape ``(2, 3, 4)`` and stride order ``(0, 1, 2)``, the stride is ``(1, 2, 6)``. This is typically also known -as column major order. If you want to create a fake tensor with compact row major order, -you should explicitly pass in ``stride_order=reversed(range(len(shape)))`` -to ``make_fake_compact_tensor``. Alternatively, you can always precisely control the -stride via the ``stride`` argument in the ``make_fake_tensor`` API. - - Error handling --------------