CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

parallel : fix cases where the input prompts can overflow the batch

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-20 19:09:25 +03:00
parent ee1d670cc6
commit ded9b43cad
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/parallel/parallel.cpp
View File

@@ -127,7 +127,9 @@ int main(int argc, char ** argv) {
llama_seq_id g_seq_id = 0;
llama_batch batch = llama_batch_init(params.n_batch, 0);
// the max batch size is as large as the context to handle cases where we get very long input prompt from multiple
// users. regardless of the size, the main loop will chunk the batch into a maximum of params.n_batch tokens at a time
llama_batch batch = llama_batch_init(params.n_ctx, 0);
int32_t n_total_prompt = 0;
int32_t n_total_gen = 0;