Commit 613016b

localai-org-maint-bot

committed

fix(llama-cpp): drop upstreamed MiniMax M3 patch

The updated llama.cpp pin already includes its specialized MiniMax M3 parser, so the vendored patch now rejects during backend preparation. Remove the temporary patch and use the upstream implementation. Assisted-by: Codex:gpt-5

1 parent 181179c commit 613016bCopy full SHA for 613016b

1 file changed

backend/cpp/llama-cpp/patches
- 0001-add-minimax-m3-chat-parser.patch

`‎backend/cpp/llama-cpp/patches/0001-add-minimax-m3-chat-parser.patch‎`

This file was deleted.

Comments

(0)