]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
server : disable speculative decoding for SWA models (#13970)
authorGeorgi Gerganov <redacted>
Mon, 2 Jun 2025 18:34:40 +0000 (21:34 +0300)
committerGitHub <redacted>
Mon, 2 Jun 2025 18:34:40 +0000 (21:34 +0300)
commit363757628848a27a435bbf22ff9476e9aeda5f40
treef2e49a64d299a7b32a5a1a13f7c8d981de1dd7c2
parentea394d7ab1f8101716d48ce9421c94c71b93a00f
server : disable speculative decoding for SWA models (#13970)

* server : use swa-full fo draft context

ggml-ci

* server : disable speculative decoding for SWA models
tools/server/server.cpp