tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-29 13:43:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

simple-chat : fix context-exceeded condition (#14494)

Browse Source 
* simple-chat : fix context-exceeded condition

ggml-ci

* cont : fix n_ctx_used computation

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-02 14:12:07 +03:00
committed by GitHub
parent c8a4e470f6
commit d7f5f4e578
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/simple-chat/simple-chat.cpp
View File

@@ -113,15 +113,16 @@ 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_memory_seq_pos_max(llama_get_memory(ctx), 0);
int n_ctx_used = llama_memory_seq_pos_max(llama_get_memory(ctx), 0) + 1;
if (n_ctx_used + batch.n_tokens > n_ctx) {
printf("\033[0m\n");
fprintf(stderr, "context size exceeded\n");
exit(0);
}
if (llama_decode(ctx, batch)) {
GGML_ABORT("failed to decode\n");
int ret = llama_decode(ctx, batch);
if (ret != 0) {
GGML_ABORT("failed to decode, ret = %d\n", ret);
}
// sample the next token