mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-21 05:19:20 +00:00
[CK_TILE] moe sorting optimize local_token (#2469)
* fix bug in loops that need use local tokens to compute
* support extra chain local_token
* update
* update
* refine some main
* update
* support dispatch_policy
* fix 15 example
[ROCm/composable_kernel commit: cfe211cc60]
This commit is contained in:
@@ -399,7 +399,7 @@ bool run(const ck_tile::ArgParser& arg_parser)
|
||||
|
||||
// if return zero, means no need workspace, can set moe_sorting_args.p_ws to nullptr
|
||||
ck_tile::index_t workspace_size =
|
||||
ck_tile::moe_sorting_get_workspace_size(tokens, experts, topk);
|
||||
ck_tile::moe_sorting_get_workspace_size(tokens, experts, topk, 0 /*dispatch_policy*/);
|
||||
ck_tile::DeviceMem moe_sorting_ws(workspace_size != 0 ? workspace_size : 0);
|
||||
if(workspace_size != 0)
|
||||
moe_sorting_ws.SetZero(); // note, clear here!!!!
|
||||
|
||||
Reference in New Issue
Block a user