]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
server : add speculative decoding support (#10455)
authorGeorgi Gerganov <redacted>
Mon, 25 Nov 2024 14:31:38 +0000 (16:31 +0200)
committerGitHub <redacted>
Mon, 25 Nov 2024 14:31:38 +0000 (16:31 +0200)
commit9ca2e677626fce759d5d95c407c03677b9c87a26
tree3b3722f3a7b1ab745b04d0b7a2f71daa280de56f
parent5931c1f233c616083d64e41a228249d58e039aa5
server : add speculative decoding support (#10455)

* server : add speculative decoding support

ggml-ci

* server : add helper function slot.can_speculate()

ggml-ci
examples/server/server.cpp