thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama: print memory breakdown on exit (#15860)

Browse source 
* llama: print memory breakdown on exit
This commit is contained in:
Johannes Gäßler 2025-09-24 16:53:48 +02:00 • committed by GitHub
parent f2a789e334
commit e789095502
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
18 changed files with 243 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/llama-memory.h
View file

@ -2,6 +2,7 @@
#include "llama.h"
#include <map>
#include <memory>
#include <functional>
@ -108,6 +109,8 @@ struct llama_memory_i {
virtual llama_pos seq_pos_min(llama_seq_id seq_id) const = 0;
virtual llama_pos seq_pos_max(llama_seq_id seq_id) const = 0;
virtual std::map<ggml_backend_buffer_type_t, size_t> memory_breakdown() const = 0;
//
// state write/read
//