ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : remove llama_kv_cache_view API + remove deprecated (#13653)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-05-20 16:13:16 +03:00 • committed by GitHub
parent b69f1647f9
commit a4090d1174
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 1 additions and 390 deletions
Download patch file Download diff file Expand all files Collapse all files

11
common/common.h
View file

@ -330,7 +330,6 @@ struct common_params {
bool use_mlock = false; // use mlock to keep model in memory
bool verbose_prompt = false; // print prompt tokens before generation
bool display_prompt = true; // print prompt before generation
bool dump_kv_cache = false; // dump the KV cache contents for debugging purposes
bool no_kv_offload = false; // disable KV offloading
bool warmup = true; // warmup run
bool check_tensors = false; // validate tensor data
@ -622,16 +621,6 @@ std::string common_detokenize(
const std::vector<llama_token> & tokens,
bool special = true);
//
// KV cache utils
//
// Dump the KV cache view with the number of sequences per cell.
void common_kv_cache_dump_view(const llama_kv_cache_view & view, int row_size = 80);
// Dump the KV cache view showing individual sequences in each cell (long output).
void common_kv_cache_dump_view_seqs(const llama_kv_cache_view & view, int row_size = 40);
//
// Embedding utils
//