ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-21 06:59:21 +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 56dceefd6b
commit ab50c6cdcb
12 changed files with 251 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
src/llama-hparams.cpp
View File

@@ -1072,6 +1072,23 @@ void llm_load_hparams(
default: model.type = e_model::MODEL_UNKNOWN;
}
} break;
case LLM_ARCH_MIMO2:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp);
ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa);
ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa);
//TODO
//hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; // which is the same as OpenAI
ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.swa_layers, hparams.n_layer);
switch (hparams.n_layer) {
case 48: model.type = e_model::MODEL_310B_A15B; break;
default: model.type = e_model::MODEL_UNKNOWN;
}
} break;
default: (void)0;
}