Commit 9ca2e67

authored

server : add speculative decoding support (#10455)

* server : add speculative decoding support ggml-ci * server : add helper function slot.can_speculate() ggml-ci

1 parent 5931c1f commit 9ca2e67Copy full SHA for 9ca2e67

1 file changed

+300

-141

lines changed

+300

-141

lines changed

Comments

(0)