Ettore Di Giacinto 9d36fcd51b backend(audio-cpp): serialize runs with a wedge-aware guard ...

audio.cpp sessions are not reentrant and a wedged CUDA call cannot be
cancelled, so a plain mutex would pile every worker thread behind a stuck GPU.
Callers waiting past the configured bound, or arriving while the holder has
already overrun it, fail fast instead.

A caller that queues behind a healthy run deliberately does not stamp the
clock: only the thread that takes the lock does. Stamping on arrival would
restart the wedge clock on every request and hide a stuck run from everyone
behind it, which is the pile-up this guard exists to prevent.

Assisted-by: Claude:claude-opus-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-07-26 01:13:02 +00:00

..

audio-cpp

backend(audio-cpp): serialize runs with a wedge-aware guard

2026-07-26 01:13:02 +00:00

bonsai

chore: ⬆️ Update PrismML-Eng/llama.cpp to 7529fdaaf99ffdc5ca71ace9c7409a56b27ad92f (#11009)

2026-07-21 15:32:26 +02:00

ds4

chore: ⬆️ Update antirez/ds4 to 0a7ad776b9068348e6cb09df8cafa9cadd285298 (#11089)

2026-07-24 18:33:57 +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 f359df4bc9a5e864029cbec4cb608e95f3500ce6 (#11107)

2026-07-24 23:52:06 +02:00

llama-cpp

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

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

privacy-filter

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

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

turboquant

fix(turboquant): supersede stale dependency bump (#11064)

2026-07-23 10:48:24 +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