]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 15e755f)
server: correct accepted tokens when need draft token replay (#26320)
authorRuixiang Wang <redacted>
Fri, 31 Jul 2026 08:16:17 +0000 (10:16 +0200)
committerGitHub <redacted>
Fri, 31 Jul 2026 08:16:17 +0000 (11:16 +0300)
commit000547513f1530346ecd163db8b3e13962949961
treeab5ee67bfd79a05bda98f505e5cce40a9198594dtree
parent15e755f30d3deb75fea2c9cc8cd129a8d7cf634dcommit | diff
server: correct accepted tokens when need draft token replay (#26320)

* spec: correct accepted tokens when need draft token replay

* cont : naming

---------

Co-authored-by: Georgi Gerganov <redacted>
tools/server/server-context.cpp diff | blob | history
Packaging of ggml-org/llama.cpp