Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-09 14:29:06 +02:00
Code Issues Packages Projects Releases Wiki Activity

server: fix n_cmpl not skipping processing

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-01-07 13:13:53 +01:00
parent ca4a8370bc
commit a9d7bcb7fc
1 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+7 -1
View File
@@ -294,7 +294,7 @@ struct server_slot {
}
bool is_child() const {
return is_processing() && task->id_parent >= 0;
return task->id_parent >= 0;
}
void release() {
@@ -2055,6 +2055,12 @@ private:
continue;
}
// check if this is a child slot
if (slot.state == SLOT_STATE_WAIT_OTHER) {
SLT_DBG(slot, "%s", "waiting for parent slot to complete\n");
continue;
}
// this slot still has a prompt to be processed
if (slot.state == SLOT_STATE_PROCESSING_PROMPT || slot.state == SLOT_STATE_STARTED) {
const auto & input_tokens = slot.task->tokens;