server: replace can_speculate() with slot.can_speculate()

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Sascha Rogmann 2026-01-02 22:42:59 +01:00 committed by GitHub
parent 9fee55e2d5
commit a7bb6b5624
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions

View File

@ -1154,7 +1154,7 @@ private:
// initialize draft batch
// TODO: rework speculative decoding [TAG_SERVER_SPEC_REWORK]
if (can_speculate()) {
if (slot.can_speculate()) {
llama_batch_free(slot.batch_spec);
slot.batch_spec = llama_batch_init(task.params.speculative.n_max + 1, 0, 1);