vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : fix free of spec context and batch (#10651)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-12-07 11:52:44 +02:00 • committed by GitHub
parent 3df784b305
commit c2a16c0bdb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -720,7 +720,7 @@ struct server_slot {
int id;
int id_task = -1;
llama_batch batch_spec;
llama_batch batch_spec = {};
llama_context * ctx_dft = nullptr;