Skip to content

LLM inference in C/C++

C++ ggml

llama: Restore quantization of mmprojs (#26818)

Pedro Cuenca86c298fb8ac1
diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 9316636d66..2e60c131d4 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -40,6 +40,8 @@
static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params & params) {
switch (arch) {
+ case LLM_ARCH_CLIP:
+ return new llama_model_clip(params);
case LLM_ARCH_LLAMA:
return new llama_model_llama(params);
case LLM_ARCH_LLAMA4:
diff --git a/src/models/clip.cpp b/src/models/clip.cpp
new file mode 100644
index 0000000000..537766aeb1
--- /dev/null
+++ b/src/models/clip.cpp
@@ -0,0 +1,18 @@
+#include "models.h"
+
+// Stub to allow llama-quantize to open mmproj GGUFs
+
+[[noreturn]]
+void llama_model_clip::load_arch_hparams(llama_model_loader &) {
+ GGML_ABORT("CLIP is a quant-only stub; load_arch_hparams should not be called");
+}
+
+[[noreturn]]
+void llama_model_clip::load_arch_tensors(llama_model_loader &) {
+ GGML_ABORT("CLIP is a quant-only stub; load_arch_tensors should not be called");
+}
+
+[[noreturn]]
+std::unique_ptr<llm_graph_context> llama_model_clip::build_arch_graph(const llm_graph_params &) const {
+ GGML_ABORT("CLIP has no inference graph via llama_model dispatch; runtime lives in tools/mtmd/clip.cpp");
+}
diff --git a/src/models/models.h b/src/models/models.h
index 12412ef534..7c813be6e6 100644
--- a/src/models/models.h
+++ b/src/models/models.h
@@ -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;