Commit graph

  • ed73b575f5
    Merge 6e6495f1ae into 1a30020a82 Richard Palethorpe 2026-05-24 09:27:01 +0000
  • 6e6495f1ae feat(gpu-detect): live VRAM usage from DRM fdinfo Richard Palethorpe 2026-05-22 12:43:01 +0100
  • 58539284e0 fix(gpu-detect): clinfo --json fallback for Intel discrete VRAM Richard Palethorpe 2026-05-22 12:03:53 +0100
  • ffc370386f
    Merge c60ed75258 into 1a30020a82 Richard Palethorpe 2026-05-24 08:42:35 +0000
  • c60ed75258 feat(middleware): Model routing, PII filtering, Cloud model proxies Richard Palethorpe 2026-05-24 09:03:13 +0100
  • 1a30020a82 ci(backend-signing): set COSIGN_EXPERIMENTAL=1 for oci-1-1 referrers mode master Ettore Di Giacinto 2026-05-24 08:21:05 +0000
  • 8bbe89a537
    fix(distributed): route per request across loaded replicas + cache probeHealth (#9968) LocalAI [bot] 2026-05-24 10:15:27 +0200
  • 1fd1702bd8 fix(distributed): log error from ShutdownModel in connection-eviction callback Ettore Di Giacinto 2026-05-24 07:57:09 +0000
  • a11b1d57cf fix(distributed): route per inference request and cache probeHealth Ettore Di Giacinto 2026-05-24 07:44:38 +0000
  • 248b56051d refactor(distributed): extract PickBestReplica from FindAndLockNodeWithModel Ettore Di Giacinto 2026-05-24 07:44:21 +0000
  • dcc5599f89
    chore: ⬆️ Update leejet/stable-diffusion.cpp to a397e03488cc27e1a42da646b82dfce9f50741c0 (#9965) LocalAI [bot] 2026-05-24 08:35:36 +0200
  • 5b66572b40
    Merge 988b9c70f1 into a95f4e63e0 LocalAI [bot] 2026-05-24 03:12:07 +0200
  • 988b9c70f1 chore(model gallery): 🤖 add new models via gallery agent mudler 2026-05-24 01:12:05 +0000
  • a95f4e63e0
    chore: ⬆️ Update ikawrakow/ik_llama.cpp to 642c038ccdf3dd08e6d9ac6fdc3b1c311ebd8a02 (#9966) LocalAI [bot] 2026-05-23 23:52:51 +0200
  • dfd19a3f88
    chore: ⬆️ Update ggml-org/llama.cpp to c0c7e147e7efa6c5858754b47259ba4880f8a906 (#9963) LocalAI [bot] 2026-05-23 23:52:36 +0200
  • d7387c725c
    feat(swagger): update swagger (#9962) LocalAI [bot] 2026-05-23 23:52:10 +0200
  • 63d84a5705
    chore: ⬆️ Update antirez/ds4 to 444afce822057d87f14c4dec307dce24fd49b3ee (#9964) LocalAI [bot] 2026-05-23 23:51:53 +0200
  • bd6a0da864
    Merge 328166617d into 1198d10b58 LocalAI [bot] 2026-05-23 22:22:47 +0200
  • 6866d05b14 ⬆️ Update ikawrakow/ik_llama.cpp mudler 2026-05-23 20:22:46 +0000
  • f560c120e3 ⬆️ Update antirez/ds4 mudler 2026-05-23 20:22:45 +0000
  • 8f3a6f9c6b ⬆️ Update leejet/stable-diffusion.cpp mudler 2026-05-23 20:22:45 +0000
  • e1d5231529 ⬆️ Update ggml-org/llama.cpp mudler 2026-05-23 20:22:44 +0000
  • 328166617d ⬆️ Update TheTom/llama-cpp-turboquant mudler 2026-05-23 20:22:44 +0000
  • a7874492c9 feat(swagger): update swagger mudler 2026-05-23 20:16:33 +0000
  • 72839967c5
    Merge 4d5a5db402 into 1198d10b58 Ching 2026-05-24 04:02:38 +0800
  • 4d5a5db402
    Merge branch 'master' into feature/add-cajal-gallery-model Ching 2026-05-23 13:02:36 -0700
  • 867f59f88a
    Merge bfc9172aac into 1198d10b58 TLoE419 2026-05-23 13:00:55 -0700
  • a1029ece51
    Merge 63313dcdb9 into 1198d10b58 dependabot[bot] 2026-05-23 15:08:26 +0200
  • 1198d10b58
    fix(traces): cap backend trace Data to keep admin UI responsive (#9960) LocalAI [bot] 2026-05-23 14:50:40 +0200
  • 17e3604116 chore(model gallery): 🤖 add new models via gallery agent mudler 2026-05-23 12:32:36 +0000
  • 96f0ad90c6 test(react-ui): disambiguate Max Items locator after adding Max Body Bytes Ettore Di Giacinto 2026-05-23 10:37:10 +0000
  • a0f3e26245
    fix(distributed): make admin backend installs resilient and observable (#9958) LocalAI [bot] 2026-05-23 12:35:44 +0200
  • 8849701418 fix(react-ui): expose tracing_max_body_bytes in Settings and Traces panels Ettore Di Giacinto 2026-05-23 09:43:42 +0000
  • 831573efde fix(traces): cap backend trace Data field so the admin UI stays responsive Ettore Di Giacinto 2026-05-23 08:09:32 +0000
  • 49b285e087 refactor(distributed): extract NodeStatus and Phase enums to constants Ettore Di Giacinto 2026-05-23 07:30:26 +0000
  • a262b06405 refactor(config): move DistributedConfig.Validate flag names to constants Ettore Di Giacinto 2026-05-23 07:21:43 +0000
  • 4d6425f03b docs(distributed): strip implementation details from user-facing docs Ettore Di Giacinto 2026-05-23 07:19:10 +0000
  • 485ebc1179 fix(galleryop): UpdateStatus preserves Nodes when caller sends none Ettore Di Giacinto 2026-05-23 07:14:40 +0000
  • e4cc1f11f3
    chore: ⬆️ Update ggml-org/llama.cpp to 1acee6bf8939948f9bcbf4b14034e4b475f06069 (#9952) LocalAI [bot] 2026-05-23 08:38:29 +0200
  • 6ed269d0b9
    chore: ⬆️ Update ggml-org/whisper.cpp to 0ccd896f5b882628e1c077f9769735ef4ce52860 (#9954) LocalAI [bot] 2026-05-23 08:37:26 +0200
  • 5756fb046d
    chore: ⬆️ Update leejet/stable-diffusion.cpp to 0baf721215f45335a5df8caf0ecb34e870c956e7 (#9955) LocalAI [bot] 2026-05-23 08:37:10 +0200
  • 66eb1072f2
    Merge 56697ebaac into 7980629bc5 qxo 2026-05-23 12:09:34 +0800
  • 75714b498a
    Merge a37f6c4501 into 7980629bc5 Adhik Joshi 2026-05-23 12:09:31 +0800
  • 200b41e2ad
    Merge d409ff3349 into 7980629bc5 avianion 2026-05-23 12:09:29 +0800
  • f61cb2d25b
    Merge 733d573660 into 7980629bc5 neil from camb.ai 2026-05-23 12:09:28 +0800
  • 6dc01afda5
    Merge c703a03247 into 7980629bc5 Dream 2026-05-23 12:09:26 +0800
  • 0f1382228d
    Merge 32bf390fae into 7980629bc5 Octopus 2026-05-23 12:09:23 +0800
  • ab66135e7a
    Merge 82ec9435a3 into 7980629bc5 Leoy 2026-05-23 12:09:21 +0800
  • d96a80980c
    Merge 349c9d2755 into 7980629bc5 Adira 2026-05-23 12:09:18 +0800
  • b1cbf39b04
    Merge 1a3cc5abd8 into 7980629bc5 LocalAI [bot] 2026-05-23 12:09:15 +0800
  • 8753e099b4
    Merge b5f3a2aabf into 7980629bc5 Andreas Egli 2026-05-23 12:09:13 +0800
  • 80acb203ac
    Merge f0a672721f into 7980629bc5 OrbisAI Security 2026-05-23 12:09:01 +0800
  • db0b6d5f9b
    Merge 8597525218 into 7980629bc5 LocalAI [bot] 2026-05-23 12:08:58 +0800
  • 83f8a5a421 chore(model gallery): 🤖 add new models via gallery agent mudler 2026-05-23 01:06:55 +0000
  • 969cb850b5 docs(distributed): document per-node breakdown in the operations bar Ettore Di Giacinto 2026-05-22 22:52:12 +0000
  • 6240e16ad8 feat(ui): per-node breakdown in OperationsBar Ettore Di Giacinto 2026-05-22 22:50:51 +0000
  • 780e720593 feat(operations): expose per-node breakdown on /api/operations Ettore Di Giacinto 2026-05-22 22:47:11 +0000
  • a72649b486 feat(distributed): write per-node OpStatus entries during install fan-out Ettore Di Giacinto 2026-05-22 22:44:18 +0000
  • f96df5eb85 feat(galleryop): UpdateNodeProgress merges per-node ticks by NodeID Ettore Di Giacinto 2026-05-22 22:35:11 +0000
  • e14d9ae8e3 feat(galleryop): add NodeProgress + OpStatus.Nodes for per-node breakdown Ettore Di Giacinto 2026-05-22 22:32:01 +0000
  • 7980629bc5
    Fix backend manifest merge signing on current cosign releases (#9957) Copilot 2026-05-23 00:20:28 +0200
  • 8fbf18490e
    fix: remove deprecated cosign bundle flag from backend merge workflow copilot/fix-backend-merge-jobs-failure copilot-swe-agent[bot] 2026-05-22 22:16:44 +0000
  • a97dc3bf57 docs(distributed): note progress-event ordering trade-off in InstallBackend Ettore Di Giacinto 2026-05-22 22:15:08 +0000
  • b334a77405
    Initial plan copilot-swe-agent[bot] 2026-05-22 22:13:44 +0000
  • a560329430 docs(distributed): document install progress streaming Ettore Di Giacinto 2026-05-22 22:06:50 +0000
  • 07b2e4e703 test(distributed): InstallBackend tolerates silent (pre-Phase-2) workers Ettore Di Giacinto 2026-05-22 22:06:08 +0000
  • f03aacf7e7 feat(distributed): forward backend install progress into galleryop OpStatus Ettore Di Giacinto 2026-05-22 22:00:49 +0000
  • d0a59be9de
    chore: ⬆️ Update ikawrakow/ik_llama.cpp to b3d39cff8bffbd67296d6badd4076a1486a0715c (#9953) LocalAI [bot] 2026-05-22 23:58:48 +0200
  • e8e75aadb6 feat(distributed): RemoteUnloaderAdapter subscribes to install progress Ettore Di Giacinto 2026-05-22 21:46:33 +0000
  • 352ebe241d feat(distributed): worker publishes debounced install progress over NATS Ettore Di Giacinto 2026-05-22 21:32:38 +0000
  • c851768163 style(messaging): drop em-dash from BackendInstallProgress test comment Ettore Di Giacinto 2026-05-22 21:22:43 +0000
  • 58f29496e5 feat(messaging): add BackendInstallProgressEvent wire type and subject Ettore Di Giacinto 2026-05-22 21:20:13 +0000
  • 63313dcdb9
    chore(deps): bump qs dependabot/npm_and_yarn/core/http/react-ui/npm_and_yarn-05b1f1d78b dependabot[bot] 2026-05-22 21:17:01 +0000
  • 871f5e0b7a feat(distributed): clear pending install rows when backend.list confirms Ettore Di Giacinto 2026-05-22 21:04:31 +0000
  • 5cda4f1ccf
    fix(L4T13 backends): switch vllm/sglang/vllm-omni to PyPI aarch64+cu130 wheels (#9950) LocalAI [bot] 2026-05-22 23:01:22 +0200
  • 148fb1c0d3 docs(distributed): document LOCALAI_NATS_BACKEND_INSTALL_TIMEOUT / _UPGRADE_TIMEOUT Ettore Di Giacinto 2026-05-22 20:58:14 +0000
  • fbb20ed2b3 test(distributed): end-to-end install-timeout-then-reconcile Ettore Di Giacinto 2026-05-22 20:40:56 +0000
  • b386d878c6 ⬆️ Update ggml-org/whisper.cpp mudler 2026-05-22 20:38:02 +0000
  • b43355fb1c ⬆️ Update leejet/stable-diffusion.cpp mudler 2026-05-22 20:38:02 +0000
  • 51adc8a831 ⬆️ Update ggml-org/llama.cpp mudler 2026-05-22 20:38:00 +0000
  • 3ce8c521a3 ⬆️ Update ikawrakow/ik_llama.cpp mudler 2026-05-22 20:38:00 +0000
  • 17ea9f93f9 feat(galleryop): surface ErrWorkerStillInstalling as non-error OpStatus Ettore Di Giacinto 2026-05-22 20:34:30 +0000
  • 4b66c3ad45 fix(distributed): don't increment Attempts on in-flight install timeout Ettore Di Giacinto 2026-05-22 20:32:59 +0000
  • 169ff75633 feat(distributed): treat NATS install timeout as in-progress, not failure Ettore Di Giacinto 2026-05-22 20:25:13 +0000
  • 073eee5190
    Merge b6fed26271 into c500461c69 LocalAI [bot] 2026-05-22 22:21:06 +0200
  • 6265ca0ee9 fix(sglang): drop [all] extra on l4t13 - xatlas has no aarch64 wheel Ettore Di Giacinto 2026-05-22 20:19:28 +0000
  • 4f89882057 feat(distributed): introduce galleryop.ErrWorkerStillInstalling sentinel Ettore Di Giacinto 2026-05-22 20:08:45 +0000
  • c500461c69
    feat(config): default prompt_cache_all to true (#9951) LocalAI [bot] 2026-05-22 22:06:22 +0200
  • 834ecc36bf
    fix(react-ui): unify backend-logs entry point for distributed mode (#9949) LocalAI [bot] 2026-05-22 22:00:08 +0200
  • 7a7b695d6a fix(sglang,vllm-omni): switch L4T13 backends to PyPI aarch64+cu130 wheels Ettore Di Giacinto 2026-05-22 19:56:44 +0000
  • f9b47c6eab feat(distributed): inject NATS install/upgrade timeouts into RemoteUnloaderAdapter Ettore Di Giacinto 2026-05-22 19:56:43 +0000
  • 66963f49db refactor(vllm): retire l4t13 pyproject.toml in favor of requirements-*.txt Ettore Di Giacinto 2026-05-22 19:46:13 +0000
  • 4306b730ed feat(cli): surface LOCALAI_NATS_BACKEND_INSTALL_TIMEOUT and _UPGRADE_TIMEOUT Ettore Di Giacinto 2026-05-22 19:46:04 +0000
  • 71d940f1e0 style(distributed): gofmt alignment after timeout fields Ettore Di Giacinto 2026-05-22 19:44:17 +0000
  • e0c22e308e feat(config): default prompt_cache_all to true Ettore Di Giacinto 2026-05-22 19:43:03 +0000
  • 0e2b84d8e3 feat(distributed): add configurable NATS backend install/upgrade timeouts Ettore Di Giacinto 2026-05-22 19:39:54 +0000
  • 5411c788f4 fix(react-ui): unify backend-logs entry point for distributed mode Ettore Di Giacinto 2026-05-22 19:36:45 +0000
  • 2de6ca51d4 fix(vllm): switch L4T13 backend to PyPI aarch64+cu130 wheels Ettore Di Giacinto 2026-05-22 19:32:04 +0000
  • b8c2f83705
    Merge e02078d761 into 61bf34ea2f dependabot[bot] 2026-05-23 01:23:45 +0800
  • 015d11077a
    Merge fd80c9b971 into 61bf34ea2f dependabot[bot] 2026-05-23 01:23:37 +0800