Richard Palethorpe 9c43b2da8f fix(model): make backend shutdown model-scoped (#10865) ...

Avoid holding the global loader lock across backend lifecycle waits and propagate forced shutdown through distributed workers. Track parallel requests with in-flight counters and reserve worker ports until process termination.

Add focused race tests and an authoritative FizzBee lifecycle model with a fail-closed conformance target.

Assisted-by: Codex:GPT-5 [FizzBee] [Ginkgo]

Signed-off-by: Richard Palethorpe <io@richiejp.com>

2026-07-19 08:43:17 +02:00

..

prefixcache

feat: prefix-cache-aware routing for distributed mode (#10071)

2026-05-30 23:24:22 +02:00

distributed_store_test.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

distributed_store.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

file_stager_http.go

feat(distributed): resumable file uploads via HTTP Content-Range (#10109)

2026-05-31 11:02:20 +00:00

file_stager_s3.go

feat: track files being staged (#9275)

2026-04-08 14:33:58 +02:00

file_stager.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

file_staging_client.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

file_staging_tts_test.go

[voice] feat: add managed voice cloning profiles (#10799)

2026-07-13 09:54:46 +02:00

file_transfer_server_test.go

feat(distributed): enforce registration token for worker file transfer (#10183)

2026-06-05 14:34:28 +02:00

file_transfer_server.go

feat(distributed): enforce registration token for worker file transfer (#10183)

2026-06-05 14:34:28 +02:00

health_mock_test.go

feat(realtime): Semantic VAD EOU token (#10444)

2026-06-30 09:01:22 +02:00

health_test.go

fix(distributed): cascade-clean stale node_models rows + filter routing by healthy status (#9754)

2026-05-13 21:57:50 +02:00

health.go

fix(distributed): cascade-clean stale node_models rows + filter routing by healthy status (#9754)

2026-05-13 21:57:50 +02:00

inflight_test.go

feat(realtime): Semantic VAD EOU token (#10444)

2026-06-30 09:01:22 +02:00

inflight.go

refactor(distributed): make in-flight tracking coverage a compile-time contract (#10476)

2026-06-24 11:08:29 +02:00

install_progress_publisher_test.go

fix(distributed): make admin backend installs resilient and observable (#9958)

2026-05-23 12:35:44 +02:00

install_progress_publisher.go

fix(distributed): make admin backend installs resilient and observable (#9958)

2026-05-23 12:35:44 +02:00

interfaces.go

fix(distributed): self-heal stale 'model not loaded' routing (#10181)

2026-06-05 09:01:36 +02:00

managers_distributed_test.go

fix(distributed): make per-node backend upgrade actually upgrade (#10838)

2026-07-15 09:16:55 +02:00

managers_distributed.go

fix(distributed): make per-node backend upgrade actually upgrade (#10838)

2026-07-15 09:16:55 +02:00

model_router_test.go

feat: prefix-cache-aware routing for distributed mode (#10071)

2026-05-30 23:24:22 +02:00

model_router.go

feat(distributed): gated X-LocalAI-Node response header (middleware + wrapper) (#9976)

2026-05-25 10:51:48 +02:00

nodes_suite_test.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

pending_op_cleanup_test.go

fix: distributed backend reinstall/upgrade UI stuck on 'reinstalling' (#10214)

2026-06-08 10:03:02 +02:00

probe_cache_test.go

fix(distributed): route per request across loaded replicas + cache probeHealth (#9968)

2026-05-24 08:15:27 +00:00

probe_cache.go

fix(distributed): route per request across loaded replicas + cache probeHealth (#9968)

2026-05-24 08:15:27 +00:00

reconciler_test.go

feat(distributed): declarative per-model scheduling via env/args (#10308)

2026-06-13 18:31:06 +02:00

reconciler.go

feat(distributed): declarative per-model scheduling via env/args (#10308)

2026-06-13 18:31:06 +02:00

registry_test.go

fix(nodes): show a node's existing labels on the detail view (#10529)

2026-06-26 23:06:42 +02:00

registry_vrambudget_test.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

registry.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

replicapicker.go

refactor(routing): extract replica picker into pkg/clusterrouting (#10123)

2026-06-01 09:38:55 +02:00

router_dirstage_test.go

feat: materialize Hugging Face model artifacts (#10825)

2026-07-15 01:09:33 +02:00

router_hardware_internal_test.go

fix(config): only inject llama.cpp serving options on the llama.cpp path (#10822)

2026-07-14 17:46:15 +02:00

router_optionstage_test.go

fix(distributed): stage backend companion assets to remote nodes (#10330)

2026-06-14 16:42:59 +02:00

router_sharedmodels_test.go

feat(distributed): add LOCALAI_DISTRIBUTED_SHARED_MODELS to skip staging on shared volumes (#10556) (#10566)

2026-06-28 01:23:07 +02:00

router_staging_context_test.go

fix(distributed): detach cold-load staging from the request context (#10438)

2026-06-22 09:06:20 +02:00

router_test.go

fix(distributed): don't let a dead worker pin the model-load advisory lock (#10600)

2026-07-02 09:52:51 +02:00

router_vrambudget_test.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

router.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

scheduling_seed_test.go

feat(distributed): declarative per-model scheduling via env/args (#10308)

2026-06-13 18:31:06 +02:00

scheduling_seed.go

feat(distributed): declarative per-model scheduling via env/args (#10308)

2026-06-13 18:31:06 +02:00

staging_keys_test.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

staging_keys.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

staging_progress_broadcast_test.go

fix(distributed): broadcast file-staging progress across replicas (#10440)

2026-06-22 09:28:07 +02:00

staging_progress.go

fix(distributed): broadcast file-staging progress across replicas (#10440)

2026-06-22 09:28:07 +02:00

unloader_test.go

fix(model): make backend shutdown model-scoped (#10865)

2026-07-19 08:43:17 +02:00

unloader_upgrade_test.go

fix: distributed backend reinstall/upgrade UI stuck on 'reinstalling' (#10214)

2026-06-08 10:03:02 +02:00

unloader.go

fix(model): make backend shutdown model-scoped (#10865)

2026-07-19 08:43:17 +02:00