vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-09 14:24:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

decrease compute buf from available memory

Browse source
This commit is contained in:
Lizonghang 2024-11-29 11:15:54 +04:00
parent 329d084061
commit 0f73d12247
3 changed files with 53 additions and 4 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 compute buffer size, including input tensors and activations
LLAMA_API uint64_t llama_model_compute_buf_size(const struct llama_model * model, const struct llama_context_params cparams, bool compress_memory);
// 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);