localai-org-maint-bot 40bae01e40 fix(llama-cpp): preserve GPU layers during option passthrough ...

Stage the negative GPU-layer sentinels expected by the upstream argument parser, then restore LocalAI resolved values unless a passthrough flag explicitly overrides them. This avoids the parser assertion that terminated the backend for any generic option.

Assisted-by: Codex:gpt-5

2026-07-29 14:10:03 +00:00

..

bonsai

feat(classifier/VAD): support voice control on low power devices (#10804)

2026-07-29 12:50:22 +02:00

ds4

chore: ⬆️ Update antirez/ds4 to 54b36ed9ba42da31b24f2d1a5feb075c2475dbb1 (#11178)

2026-07-29 08:45:31 +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 b054a8b983827c01aec59d4dc273a27c492c51c4 (#11175)

2026-07-29 09:57:23 +02:00

llama-cpp

fix(llama-cpp): preserve GPU layers during option passthrough

2026-07-29 14:10:03 +00:00

privacy-filter

fix(distributed): reject wrong-model requests on the remaining modalities (#10990)

2026-07-20 21:58:19 +02:00

turboquant

feat(classifier/VAD): support voice control on low power devices (#10804)

2026-07-29 12:50:22 +02:00

run-unit-tests.sh

fix(process): give backend workers a parent-death safety net (#10639)

2026-07-02 19:16:48 +02:00