mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-15 18:13:29 +02:00
86c298fb8a
* Restore quantization of mmprojs This was lost in the refactor undertaken in #22004. * add noreturn --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
19 lines
636 B
C++
19 lines
636 B
C++
#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");
|
|
}
|