ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 16:39:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding Ling/Ring (a.k.a., Bailing-MoE2) support (#833)

Browse Source 
* Adding Ling/Ring (a.k.a., Bailing-MoE2)

* Add expert group selection (not working, so turned off)

* BailingMoE2 conversion

* WIP

* Bits and pieces

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-10-15 14:20:40 +03:00
committed by GitHub
parent ba9fefb73d
commit f7adde1043
25 changed files with 1295 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
src/llama-hparams.cpp
View File

@@ -894,6 +894,31 @@ void llm_load_hparams(
default: model.type = e_model::MODEL_UNKNOWN;
}
} break;
case LLM_ARCH_BAILINGMOE2:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead);
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp);
ml.get_key(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_shexp);
ml.get_key(LLM_KV_EXPERT_SHARED_COUNT, hparams.n_expert_shared);
ml.get_key(LLM_KV_EXPERT_GROUP_COUNT, hparams.n_expert_groups);
ml.get_key(LLM_KV_EXPERT_GROUP_USED_COUNT, hparams.n_group_used);
ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale);
ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false);
ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func);
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers, false);
// TODO: when MTP is implemented, this should probably be updated if needed
hparams.n_layer_kv_from_start = hparams.n_layer - hparams.nextn_predict_layers;
switch (hparams.n_layer) {
case 20: model.type = MODEL_16B_A1B; break;
case 21: model.type = MODEL_16B_A1B; break;
case 32: model.type = MODEL_100B_A6B; break;
case 33: model.type = MODEL_100B_A6B; break;
default: model.type = e_model::MODEL_UNKNOWN;
}
} break;
case LLM_ARCH_DOTS1:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);