mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

model, mtmd: fix gguf conversion for audio/vision mmproj (#21309)

Browse Source 
* fix gguf conversion for audio/vision mmproj

* fix test
This commit is contained in:
Xuan-Son Nguyen
2026-04-02 17:10:32 +02:00
committed by GitHub
parent 223373742b
commit 63f8fe0ef4
27 changed files with 1462 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.h
+7
View File
@@ -270,6 +270,9 @@ struct llama_layer {
struct ggml_tensor * ffn_norm = nullptr;
struct ggml_tensor * ffn_norm_b = nullptr;
struct ggml_tensor * ffn_post_norm = nullptr;
struct ggml_tensor * ffn_post_norm_1 = nullptr; // gemma4
struct ggml_tensor * ffn_post_norm_2 = nullptr; // gemma4
struct ggml_tensor * ffn_pre_norm_2 = nullptr; // gemma4
struct ggml_tensor * layer_out_norm = nullptr;
struct ggml_tensor * layer_out_norm_b = nullptr;
struct ggml_tensor * ffn_norm_exps = nullptr;
@@ -285,6 +288,7 @@ struct llama_layer {
// ff MoE
struct ggml_tensor * ffn_gate_inp = nullptr;
struct ggml_tensor * ffn_gate_inp_s = nullptr; // gemma4
struct ggml_tensor * ffn_gate_exps = nullptr;
struct ggml_tensor * ffn_down_exps = nullptr;
struct ggml_tensor * ffn_up_exps = nullptr;
@@ -483,6 +487,9 @@ struct llama_layer {
struct ggml_tensor * indexer_attn_k = nullptr;
struct ggml_tensor * indexer_attn_q_b = nullptr; // note: for lora a/b, not bias
// gemma4 layer output scale
struct ggml_tensor * out_scale = nullptr;
struct llama_layer_posnet posnet;
struct llama_layer_convnext convnext;