Ettore Di Giacinto e28e80857b

feat(shutdown): allow force shutdown of backends (#3733) ...

We default to a soft kill, however, we might want to force killing
backends after a while to avoid hanging requests (which may hallucinate
indefinetly)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2024-10-05 10:41:35 +02:00

..

filters.go

chore(refactor): drop duplicated shutdown logics (#3589)

2024-09-17 16:51:40 +02:00

initializers.go

feat(multimodal): allow to template placeholders (#3728)

2024-10-04 18:32:29 +02:00

loader_test.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

loader.go

feat(shutdown): allow force shutdown of backends (#3733)

2024-10-05 10:41:35 +02:00

model_suite_test.go

tests: add template tests (#2063)

2024-04-18 10:57:24 +02:00

model.go

chore(refactor): track grpcProcess in the model structure (#3663)

2024-09-26 12:44:55 +02:00

options.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

process.go

fix(initializer): correctly reap dangling processes (#3717)

2024-10-02 20:37:40 +02:00

template_test.go

fix(model-loading): keep track of open GRPC Clients (#3377)

2024-08-25 14:36:09 +02:00

template.go

fix(model-loading): keep track of open GRPC Clients (#3377)

2024-08-25 14:36:09 +02:00

watchdog.go

fix(model-loading): keep track of open GRPC Clients (#3377)

2024-08-25 14:36:09 +02:00