CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

parallel : example for serving multiple users in parallel

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-18 20:30:05 +03:00
parent 1f17ea631c
commit 0161372b9a
9 changed files with 262 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/perplexity/perplexity.cpp
View File

@@ -681,7 +681,7 @@ int main(int argc, char ** argv) {
return 1;
}
params.perplexity = true;
params.logits_all = true;
params.n_batch = std::min(params.n_batch, params.n_ctx);
if (params.ppl_stride > 0) {