LocalAI [bot]
|
7637f8cf1b
|
feat(distributed): declarative per-model scheduling via env/args (#10308)
* feat(distributed): add SpreadAll column and authoritative scheduling seeding
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed): parse declarative model scheduling config (env/file)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed): reconcile spread_all to one replica per matching node
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed): wire LOCALAI_MODEL_SCHEDULING env/args and startup seeding
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed): expose spread_all on the scheduling API endpoint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(distributed): add spread-to-all-nodes mode to the scheduling UI
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* docs(distributed): document LOCALAI_MODEL_SCHEDULING env/args
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* docs(distributed): clarify replica modes and all-nodes spread in scheduling config
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
2026-06-13 18:31:06 +02:00 |
|