Skip to content

LLM inference in C/C++

C++ ggml

model: fix granite3 moe unknown parameter count (#28632)

Aaron Teoe2d2c0d6aa9b
diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 0adc07449b..54009b3696 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -935,6 +935,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_17B_16E: return "17Bx16E (Scout)";
case LLM_TYPE_17B_128E: return "17Bx128E (Maverick)";
case LLM_TYPE_A13B: return "A13B";
+ case LLM_TYPE_1B_A400M: return "1B.A400M";
case LLM_TYPE_7B_A1B: return "7B.A1B";
case LLM_TYPE_8B_A1B: return "8B.A1B";
case LLM_TYPE_7_9B_A1_3B: return "7.9B.A1.3B";
diff --git a/src/llama-model.h b/src/llama-model.h
index 4c4a30e018..c0cc406556 100644
--- a/src/llama-model.h
+++ b/src/llama-model.h
@@ -116,6 +116,7 @@ enum llm_type {
LLM_TYPE_17B_16E, // llama4 Scout
LLM_TYPE_17B_128E, // llama4 Maverick
LLM_TYPE_A13B,
+ LLM_TYPE_1B_A400M, // Granite3 MoE
LLM_TYPE_7B_A1B,
LLM_TYPE_8B_A1B, // lfm2moe
LLM_TYPE_7_9B_A1_3B, // Ling-3.0-tiny
diff --git a/src/models/granite-moe.cpp b/src/models/granite-moe.cpp
index 09be49393e..156553edfd 100644
--- a/src/models/granite-moe.cpp
+++ b/src/models/granite-moe.cpp
@@ -8,6 +8,7 @@ void llama_model_granite_moe::load_arch_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_SCALE, hparams.f_attention_scale, false);
switch (hparams.n_layer()) {
+ case 24: type = LLM_TYPE_1B_A400M; break;
case 32: type = LLM_TYPE_3B; break;
case 40: type = LLM_TYPE_3B; break;
// Add additional layer/vocab/etc checks here for other model sizes