root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 03:44:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

server : bug fix in ingest_images

Browse Source 
n_tokens is incremented internally by llama_batch_add
This commit is contained in:
Georgi Gerganov 2023-10-19 14:43:19 +03:00
parent a8c981b734
commit 3d5929e8ee
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
examples/server/server.cpp
View File

@ -963,7 +963,6 @@ struct llama_server_context
{
llama_batch_add(batch, append_tokens[i], slot.n_past, { slot.id }, true);
slot.n_past += 1;
batch.n_tokens += 1;
}
}
return true;