In distributed mode, even when the frontend and workers share the same
models directory via a shared volume mount, starting a model on a worker
re-staged (re-downloaded) it: stageModelFiles always uploads model files
into a tracking-key-namespaced subdir on the worker, and the staging probe
only checks that staged location, so a file already present on the shared
volume at the canonical path was never reused.
Add a config switch LOCALAI_DISTRIBUTED_SHARED_MODELS (default false). When
enabled, the operator asserts that all nodes mount the SAME models directory
at the SAME path, so staging is unnecessary: the frontend's absolute model
paths are already valid on the worker. In that mode stageModelFiles returns
the cloned opts unchanged without uploading, leaving the path fields pointing
at their canonical absolute paths so the worker loads them directly from the
shared volume.
The value is plumbed from DistributedConfig through SmartRouterOptions into
the SmartRouter. Docs and docker-compose.distributed.yaml updated.
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
The Dockerfile's HEALTHCHECK probes http://localhost:8080/readyz, which
is the OpenAI API server port. When the same image runs as a worker, it
listens on the gRPC base port (50051) and an HTTP file transfer server
on port-1 (50050) — nothing on 8080 — so docker always reports the
container as unhealthy.
Add unauthenticated /readyz and /healthz endpoints to the worker's HTTP
file transfer server, and override HEALTHCHECK_ENDPOINT for worker-1 in
the distributed compose file. Disable the healthcheck for agent-worker
since it is NATS-only and exposes no HTTP server.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude-code:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
In distributed mode the Backends gallery used to fan every install out to
every worker — fine for auto-resolving (meta) backends like llama-cpp where
each node picks its own variant, but wrong for hardware-specific builds
like cpu-llama-cpp that would silently land on every GPU node.
Adds a node-targeted install path through the existing
POST /api/nodes/:id/backends/install plumbing, with two entry points:
- Backends gallery row gets a split-button in distributed mode. Auto-
resolving keeps "Install on all nodes" as the primary; chevron menu
opens the picker. Hardware-specific routes the primary directly to the
picker — no fan-out path on the row.
- Nodes-page drawer gets a "+ Add backend" button that navigates to
/app/backends?target=<node-id>; the gallery scopes itself to that node
(banner, single per-row install button, Reinstall/Remove for already-
installed). One gallery, two scopes — no second UI to maintain.
The picker (new NodeInstallPicker) shows a 3-state suitability column
(Compatible / Override / Installed), an auto-expanding variant override
disclosure that fires when selected nodes have no working GPU, parallel
per-node installs with inline status and Retry-failed-nodes, and a
mismatch confirm that names the consequence on the button itself.
A 409 fan-out guard on /api/backends/apply protects CLI/Terraform/script
users from the same footgun: hardware-specific installs in distributed
mode now return code "concrete_backend_requires_target" with a human-
readable error and a meta_alternative pointer.
The gallery list payload now surfaces capabilities, metaBackendFor and
per-row nodes (NodeBackendRef) so the picker and the new Nodes column
have everything they need without re-walking the gallery client-side.
GODEBUG=netdns=go is set on the compose services because the cgo DNS
resolver follows the container's nsswitch.conf to host systemd-resolved
(127.0.0.53), unreachable from inside the container; the pure-Go
resolver reads /etc/resolv.conf directly and uses Docker's embedded DNS.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude Code:claude-opus-4-7[1m] [Edit] [Bash] [Read] [Write]
Workers on NVIDIA unified-memory hardware (DGX Spark / GB10, Jetson AGX Thor,
Jetson Orin/Xavier/Nano) were reporting `available_vram=0` back to the frontend,
so the Nodes UI showed the node as fully used even when most of the unified
memory was actually free.
Three causes addressed:
* `isTegraDevice` only matched `/sys/devices/soc0/family == "Tegra"`. DGX Spark
(SBSA) reports JEDEC codes there instead — `jep106:0426` for the NVIDIA
manufacturer — so the Tegra/unified-memory fallback never ran. Renamed to
`isNVIDIAIntegratedGPU` and extended to also match `jep106:0426[:*]` via
`/sys/devices/soc0/soc_id`.
* The unified-iGPU code defaulted the device name to `"NVIDIA Jetson"` when
`/proc/device-tree/model` was missing. That's what happens for Thor inside a
docker container, and always on DGX Spark. New `nvidiaIntegratedGPUName`
resolves via dt-model → `/sys/devices/soc0/machine` → `soc_id` lookup
(`jep106:0426:8901` → `"NVIDIA GB10"`) so the Nodes UI labels the box
correctly.
* Worker heartbeat sent `available_vram=0` (or total-as-available) when VRAM
usage was momentarily unknown — e.g. when `nvidia-smi` intermittently failed
with `waitid: no child processes` under containers without `--init`. Each
such heartbeat overwrote the DB and made the UI flip to "fully used".
`heartbeatBody` now omits `available_vram` in that case so the DB keeps its
last good value.
Also updates the commented GPU blocks in both compose files with
`NVIDIA_DRIVER_CAPABILITIES=compute,utility`, `capabilities: [gpu, utility]`,
and `init: true`, and documents the requirement in the distributed-mode and
nvidia-l4t pages. Without `utility`, NVML/`nvidia-smi` are absent inside the
container, which is what put the DGX Spark worker into the buggy fallback in
the first place.
Detection verified on live hardware (dgx.casa / GB10 and 192.168.68.23 / Thor)
by running a cross-compiled probe of the new helpers on both host and inside
the worker container.
Assisted-by: Claude:opus-4.7 [Claude Code]
* feat: add distributed mode (experimental)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix data races, mutexes, transactions
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactorings
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix events and tool stream in agent chat
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* use ginkgo
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(cron): compute correctly time boundaries avoiding re-triggering
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* enhancements, refactorings
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* do not flood of healthy checks
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* do not list obvious backends as text backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* tests fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactoring and consolidation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Drop redundant healthcheck
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* enhancements, refactorings
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
