tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-22 07:24:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/mamba2

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-05-02 11:55:11 -04:00
parent 94c3d53043 c642bc014c
commit 929fe85db3
41 changed files with 2432 additions and 1177 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llama-model.h
View File

@@ -396,8 +396,11 @@ struct llama_model {
const struct ggml_tensor * get_tensor(const char * name) const;
ggml_tensor * get_rope_factors(uint32_t n_ctx_per_seq, int il) const;
// note: can mutate `cparams`
// TODO: move this to new llm_arch_model_i interface
llama_memory_i * create_memory() const; // TODO: params
llama_memory_i * create_memory(const llama_memory_params & params, llama_cparams & cparams) const;
// TODO: move this to new llm_arch_model_i interface
llm_graph_result_ptr build_graph(