ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-23 06:34:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Mimo-V2-Flash support (#1096)

Browse Source 
* Mimo-2 support

* Fix bug for head sizes not being the same

It still does not solve the Mimo-2 quantized cache issue.

* Fix quantized cache

* Minor

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2026-01-05 08:00:01 +02:00
committed by GitHub
parent 1401326916
commit 8a6622eb4f
12 changed files with 251 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llama.cpp
View File

@@ -4905,6 +4905,7 @@ enum llama_rope_type llama_rope_type(const struct llama_model * model) {
case LLM_ARCH_OPENAI_MOE:
case LLM_ARCH_BAILINGMOE2:
case LLM_ARCH_MINIMAX_M2:
case LLM_ARCH_MIMO2:
return LLAMA_ROPE_TYPE_NEOX;
case LLM_ARCH_QWEN2VL: