CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : add new llama_decode() API that works with llama_batch

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-18 14:23:52 +03:00
parent 58bb5110ca
commit 9f42e75489
13 changed files with 146 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@@ -434,7 +434,7 @@ struct llama_server_context
{
n_eval = params.n_batch;
}
if (llama_eval(ctx, &embd[n_past], n_eval, n_past, params.n_threads))
if (llama_decode(ctx, llama_batch_get_one(&embd[n_past], n_eval, n_past, 0), params.n_threads))
{
LOG_ERROR("failed to eval", {
{"n_eval", n_eval},