mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 00:40:09 +00:00
[CK_TILE] Fix mock token id, support g1u1/g1u0 through same inline code block (#1808)
* fix mock token id * prepare host for g1u1 * reformat inline-asm * restructure uk_0 * restructure gate_up * done * change default to init=1 * update readme * fix a bug in interleave pipeline * rcp for silu
This commit is contained in:
@@ -1,3 +1,10 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
// clang-format off
|
||||
|
||||
// define the CK_TILE_** macro before include this file to change kernel variation
|
||||
// we will undef everything defined in this file
|
||||
|
||||
#ifndef CK_TILE_FLATMM_UK_MFMA
|
||||
#define CK_TILE_FLATMM_UK_MFMA CK_TILE_FLATMM_UK_MFMA_BF16
|
||||
#endif
|
||||
@@ -816,3 +823,5 @@
|
||||
#undef _UK_MFMA_
|
||||
#undef _UK_PK_CVT_
|
||||
#undef _UK_ATOMIC_ADD_
|
||||
#undef CK_TILE_FLATMM_UK_MFMA
|
||||
// clang-format on
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user