ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 04:19:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'f161b5b738781c71bd5f2c191561b81f679ba9ed' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-09-23 23:11:18 +00:00
parent c39d5ca2c5
commit a55a7e37ec
40 changed files with 167 additions and 273 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck_tile/ops/smoothquant/kernel/moe_smoothquant_kernel.hpp
View File

@@ -138,7 +138,7 @@ struct MoeSmoothquant
const index_t i_topk = blockIdx.x;
const index_t i_token = blockIdx.y * Block_M;
const index_t i_token_in_thrd =
amd_wave_read_first_lane(threadIdx.x / Problem::BlockShape::ThreadPerBlock_N);
__builtin_amdgcn_readfirstlane(threadIdx.x / Problem::BlockShape::ThreadPerBlock_N);
const index_t i_expert = reinterpret_cast<const index_t*>(
kargs.p_topk_ids)[(i_token + i_token_in_thrd) * kargs.topk + i_topk];