LLM inference in C/C++
C++ ggml
models : fix incorrect uses of get_key_or_arr (#28868)
Sigbjørn Skjæret97e4ca735820
diff --git a/src/models/gemma4-assistant.cpp b/src/models/gemma4-assistant.cppindex 8431ec2a1f..74d06151e3 100644--- a/src/models/gemma4-assistant.cpp+++ b/src/models/gemma4-assistant.cpp@@ -4,7 +4,7 @@ void llama_model_gemma4_assistant::load_arch_hparams(llama_model_loader & ml) {hparams.n_embd_inp_impl = hparams.n_embd_out();hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;- ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer_all);+ ml.get_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl);uint32_t n_kv_shared_layers = 0;ml.get_key(LLM_KV_ATTENTION_SHARED_KV_LAYERS, n_kv_shared_layers, false);diff --git a/src/models/gemma4.cpp b/src/models/gemma4.cppindex 39e899aa6e..67de74c547 100644--- a/src/models/gemma4.cpp+++ b/src/models/gemma4.cpp@@ -2,7 +2,7 @@void llama_model_gemma4::load_arch_hparams(llama_model_loader & ml) {hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;- ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer());+ ml.get_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl);uint32_t n_kv_shared_layers = 0;ml.get_key(LLM_KV_ATTENTION_SHARED_KV_LAYERS, n_kv_shared_layers, false);diff --git a/src/models/step35.cpp b/src/models/step35.cppindex 946a369600..ca68855d8d 100644--- a/src/models/step35.cpp+++ b/src/models/step35.cpp@@ -23,7 +23,7 @@ void llama_model_step35::load_arch_hparams(llama_model_loader & ml) {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, false);- ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer_all);+ ml.get_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl);ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer_all, false);ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_SHEXP, hparams.swiglu_clamp_shexp, hparams.n_layer_all, false);