tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
2 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/speculative.cpp
View File

@ -62,6 +62,10 @@ struct common_speculative * common_speculative_init(
}
void common_speculative_free(struct common_speculative * spec) {
if (spec == nullptr) {
return;
}
common_sampler_free(spec->smpl);
llama_batch_free(spec->batch);

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;