ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 10:21:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Grouped expert routing (CPU only) (#836)

Browse Source 
* Better argsort (CPU)

* Attemt at grouped topk

* This seems to do the trick for grouped experts routing

* Cleanup

* Trying to merge, something is not right

* Working merged grouped top_k (CPU)

* Add command line option to enable grouped expert routing

* Add grouped expert routing option to llama-bench

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-10-16 14:57:02 +03:00
committed by GitHub
parent e66d307e13
commit cde642e591
11 changed files with 221 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
common/common.h
View File

@@ -235,6 +235,7 @@ struct gpt_params {
int attn_max_batch = 0; // Max batch size to use when computing attention (only applicable if flash_attn = false)
bool fused_moe_up_gate = false; // fused up*unary(gate) op for MoE models
bool fused_up_gate = true; // fused up*unary(gate) op
bool grouped_expert_routing = false; // if to use grouped expert routing (BailingMoeV2 arch)
int min_experts = -1;
float thresh_experts = 0;