ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 05:31:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] Port hw independent changes from internal repo to develop branch (#3301)

Browse Source 
* [CK_TILE] Port hw independent changes from internal repo to develop branch

It includes PR#96, #114, #120, #121.

* correct rebase error
This commit is contained in:
linqunAMD
2025-12-13 01:28:37 +08:00
committed by GitHub
parent 9869641324
commit fc7bf0ab1c
22 changed files with 465 additions and 310 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck_tile/ops/fused_moe/kernel/moe_sorting_kernel.hpp
View File

@@ -986,6 +986,8 @@ struct MoeSortingKernel
p_sorted_expert_ids[unit_size_mdiv.div(i)] = expert_id;
}
}
__syncthreads();
smem_cumdup(num_experts) = smem_cumsum(num_experts);
// fill the p_sorted_token_ids/p_sorted_weights