LLM inference in C/C++
C++ ggml
model : glm-dsa load DSA indexer tensors as optional (#24770)
davidrhodus796f41bedca8
diff --git a/src/models/glm-dsa.cpp b/src/models/glm-dsa.cppindex 11d91312de..32fe6def6f 100644--- a/src/models/glm-dsa.cpp+++ b/src/models/glm-dsa.cpp@@ -101,11 +101,11 @@ void llama_model_glm_dsa::load_arch_tensors(llama_model_loader &) {layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, flags);// DSA indexer- layer.indexer_k_norm = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM, "weight", i), {hparams.indexer_head_size}, flags);- layer.indexer_k_norm_b = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM, "bias", i), {hparams.indexer_head_size}, flags);- layer.indexer_proj = create_tensor(tn(LLM_TENSOR_INDEXER_PROJ, "weight", i), {n_embd, hparams.indexer_n_head}, flags);- layer.indexer_attn_k = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_K, "weight", i), {n_embd, hparams.indexer_head_size}, flags);- layer.indexer_attn_q_b = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_Q_B, "weight", i), {q_lora_rank, hparams.indexer_n_head * hparams.indexer_head_size}, flags);+ layer.indexer_k_norm = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM, "weight", i), {hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);+ layer.indexer_k_norm_b = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM, "bias", i), {hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);+ layer.indexer_proj = create_tensor(tn(LLM_TENSOR_INDEXER_PROJ, "weight", i), {n_embd, hparams.indexer_n_head}, flags | TENSOR_NOT_REQUIRED);+ layer.indexer_attn_k = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_K, "weight", i), {n_embd, hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);+ layer.indexer_attn_q_b = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_Q_B, "weight", i), {q_lora_rank, hparams.indexer_n_head * hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);if (i < (int) hparams.n_layer_dense_lead) {layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, flags);layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}, flags);