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

llama : update llama_kv_self API

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-01-14 16:47:34 +02:00
parent fd05ab87aa
commit 17b363afd3
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
30 changed files with 387 additions and 205 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/simple-chat/simple-chat.cpp
View file

@ -88,8 +88,6 @@ int main(int argc, char ** argv) {
return 1;
}
const llama_kv_cache * kv = llama_get_kv_cache(ctx);
// initialize the sampler
llama_sampler * smpl = llama_sampler_chain_init(llama_sampler_chain_default_params());
llama_sampler_chain_add(smpl, llama_sampler_init_min_p(0.05f, 1));
@ -100,7 +98,7 @@ int main(int argc, char ** argv) {
auto generate = [&](const std::string & prompt) {
std::string response;
const bool is_first = llama_kv_cache_used_cells(kv) == 0;
const bool is_first = llama_kv_self_used_cells(ctx) == 0;
// tokenize the prompt
const int n_prompt_tokens = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, is_first, true);
@ -115,7 +113,7 @@ int main(int argc, char ** argv) {
while (true) {
// check if we have enough space in the context to evaluate this batch
int n_ctx = llama_n_ctx(ctx);
int n_ctx_used = llama_kv_cache_used_cells(kv);
int n_ctx_used = llama_kv_self_used_cells(ctx);
if (n_ctx_used + batch.n_tokens > n_ctx) {
printf("\033[0m\n");
fprintf(stderr, "context size exceeded\n");