root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

server : fix free of spec context and batch (#10651)
Some checks are pending
Python check requirements.txt / check-requirements (push) Waiting to run
Details
flake8 Lint / Lint (push) Waiting to run
Details
Python Type-Check / pyright type-check (push) Waiting to run
Details

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
Show Stats 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;