nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

server: revert llama_decode stop (#1722) 

Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana 2026-05-02 10:19:59 -05:00 committed by GitHub
parent 9f1deefa71
commit b8eb8ccbb5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/llama.cpp
View File

@ -8477,11 +8477,6 @@ int32_t llama_encode(
int32_t llama_decode(
struct llama_context * ctx,
struct llama_batch batch) {
// Clear any leftover stop signal from a previous (already-returned) decode. llama_decode_stop()
// is intended to interrupt the decode that is currently in flight; without this reset, a stop
// that arrived after the interrupted call returned would bleed into the next decode and cause
// an immediate ret=-3, which servers interpret as a fatal decode failure.
stop_internal_decode = false;
const int ret = llama_decode_internal(*ctx, batch);
if (ret < 0) {
LLAMA_LOG_ERROR("%s: failed to decode, ret = %d\n", __func__, ret);