]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
common : delegate assistant continuation to underlying template handlers (#23089)
authorAldehir Rojas <redacted>
Sun, 17 May 2026 11:36:05 +0000 (07:36 -0400)
committerGitHub <redacted>
Sun, 17 May 2026 11:36:05 +0000 (13:36 +0200)
commit39cf5d61915769124b7efbbfa69c46f19a6363ee
tree83e909c000e38b0e9a4d4000e0220cfda1acf754
parenta6d6183dbc5e30ed7cc92c7d29fc5daccab86a9e
common : delegate assistant continuation to underlying template handlers (#23089)

* common : delegate assistant continuation to template handler

* server : implement echo parameter to exclude assistant prefill in the response

* server : fix tests for prefill

* server : use existing llama template

* cont : clean up
common/chat-auto-parser-generator.cpp
common/chat-auto-parser.h
common/chat-peg-parser.cpp
common/chat.cpp
common/chat.h
tests/test-chat.cpp
tools/server/server-common.cpp
tools/server/server-task.cpp
tools/server/server-task.h
tools/server/tests/unit/test_chat_completion.py