LocalAI

mirror of https://github.com/mudler/LocalAI.git synced 2026-07-30 18:09:05 -04:00

Files

Nandana Dileep b5e4413eab feat: add MiniMax-M3 model support (#10837 )

Adds inference parameter defaults for the minimax-m3 model family and
includes a vendored patch of upstream llama.cpp PR #24523 to recognize
the minimax-m3 architecture. Once the upstream PR merges, the patch can
be removed and LLAMA_VERSION bumped normally.

Changes:
- backend/cpp/llama-cpp/patches/0001-add-minimax-m3-support.patch:
  vendored patch from ggml-org/llama.cpp#24523 (Preliminary MiniMax-M3
  support). Applied by prepare.sh during the build; keeps the pinned
  LLAMA_VERSION pointing at the latest upstream tag.
- core/config/inference_defaults.json: add minimax-m3 family entry
  (temperature=1.0, top_p=0.95, top_k=40, min_p=0.01,
  repeat_penalty=1.0, matching the existing minimax defaults) and
  register it in the patterns list before the shorter minimax-m2.7
  entry for correct longest-match-first ordering.

Upstream: depends on ggml-org/llama.cpp#24523
Closes: https://github.com/mudler/LocalAI/issues/10820

Signed-off-by: Nandana Dileep <110280757+nandanadileep@users.noreply.github.com>

2026-07-20 08:26:51 +02:00

bonsai

fix(ci): build Bonsai backend images (#10939 ) (#10951 )

2026-07-19 11:49:07 +02:00

ds4

fix(ds4): bundle transitive runtime dependencies (#10783 )

2026-07-11 23:41:27 +02:00

grpc

fix: speedup git submodule update with --single-branch (#2847 )

2024-07-13 22:32:25 +02:00

ik-llama-cpp

chore: ⬆️ Update ikawrakow/ik_llama.cpp to 9d07d8681ece159a89fb4e16a1f9c9f3a5fac20f (#10933 )