Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

llama: Restore quantization of mmprojs (#26818)

Browse Source 
* Restore quantization of mmprojs

This was lost in the refactor undertaken in #22004.

* add noreturn

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Pedro Cuenca
2026-08-10 11:58:32 +02:00
committed by GitHub
co-authored by Xuan Son Nguyen
parent 2e2d99cfd2
commit 86c298fb8a
3 changed files with 36 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/models.h
+16
View File
@@ -386,6 +386,22 @@ struct llama_model_bloom : public llama_model_base {
};
// Quant-only stub for mmproj GGUFs
// none of these are ever called, they only exist to satisfy the llama_model_base interface
struct llama_model_clip : public llama_model_base {
llama_model_clip(const struct llama_model_params & params) : llama_model_base(params) {}
[[noreturn]]
void load_arch_hparams(llama_model_loader & ml) override;
[[noreturn]]
void load_arch_tensors(llama_model_loader & ml) override;
[[noreturn]]
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
};
struct llama_model_mpt : public llama_model_base {
llama_model_mpt(const struct llama_model_params & params) : llama_model_base(params) {}
void load_arch_hparams(llama_model_loader & ml) override;