tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

shadow : cont gcc

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-01-12 16:09:49 +02:00
parent f65e3d324d
commit 10eb87409e
12 changed files with 509 additions and 511 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/simple-chat/simple-chat.cpp
View File

@ -110,9 +110,8 @@ int main(int argc, char ** argv) {
llama_token new_token_id;
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_get_kv_cache_used_cells(ctx);
if (n_ctx_used + batch.n_tokens > n_ctx) {
if (n_ctx_used + batch.n_tokens > (int) llama_n_ctx(ctx)) {
printf("\033[0m\n");
fprintf(stderr, "context size exceeded\n");
exit(0);