CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Remove llama_model_is_hybrid_Recurrent public API

Browse Source 
https://github.com/ggml-org/llama.cpp/pull/13979#discussion_r2141728423

Branch: HybridRecurrentCache

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Gabe Goodhart
2025-06-12 14:01:28 -06:00
parent 1510016ea4
commit 7ba463b38c
2 changed files with 0 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/llama.h
View File

@@ -572,9 +572,6 @@ extern "C" {
// Returns true if the model is recurrent (like Mamba, RWKV, etc.)
LLAMA_API bool llama_model_is_recurrent(const struct llama_model * model);
// Returns true if the model is hybrid-recurrent (like Jamba, Bamba, etc.)
LLAMA_API bool llama_model_is_hybrid_recurrent(const struct llama_model * model);
// Returns 0 on success
LLAMA_API uint32_t llama_model_quantize(
const char * fname_inp,

4
src/llama-model.cpp
View File

@@ -14405,10 +14405,6 @@ bool llama_model_is_recurrent(const llama_model * model) {
return llm_arch_is_recurrent(model->arch);
}
bool llama_model_is_hybrid_recurrent(const llama_model * model) {
return llm_arch_is_hybrid_recurrent(model->arch);
}
const std::vector<std::pair<std::string, ggml_tensor *>> & llama_internal_get_tensor_map(const llama_model * model) {
return model->tensors_by_name;
}