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

kv-cache : simplify the interface (#13660)

Browse source 
* kv-cache : simplify the interface

ggml-ci

* context : revert llama_batch_allocr position change

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-05-21 15:11:13 +03:00 • committed by GitHub
parent b44890df2e
commit 797f2ac062
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 89 additions and 153 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/simple-chat/simple-chat.cpp
View file

@ -98,7 +98,7 @@ int main(int argc, char ** argv) {
auto generate = [&](const std::string & prompt) {
std::string response;
const bool is_first = llama_kv_self_used_cells(ctx) == 0;
const bool is_first = llama_kv_self_seq_pos_max(ctx, 0) == 0;
// tokenize the prompt
const int n_prompt_tokens = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, is_first, true);
@ -113,7 +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_self_used_cells(ctx);
int n_ctx_used = llama_kv_self_seq_pos_max(ctx, 0);
if (n_ctx_used + batch.n_tokens > n_ctx) {
printf("\033[0m\n");
fprintf(stderr, "context size exceeded\n");