vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-10 14:14:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

reduce kv cache from available memory

Browse source
This commit is contained in:
Lizonghang 2024-11-28 20:21:21 +04:00
parent 9858d90ce4
commit 45a1e55eec
5 changed files with 25 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

3
include/llama.h
View file

@ -523,6 +523,9 @@ extern "C" {
// Returns the total number of parameters in the model
LLAMA_API uint64_t llama_model_n_params(const struct llama_model * model);
// Return the size of KV cache in the model
LLAMA_API uint64_t llama_model_kvcache_size(const struct llama_model * model, const struct llama_context_params cparams);
// Return the total number of float operations in the model
LLAMA_API void llama_model_n_flops(
struct llama_model * model,