LocalAI

0 Fork 0

mirror of https://github.com/mudler/LocalAI.git synced 2026-09-12 22:33:54 -04:00

Files

T

Ettore Di Giacinto 2c68fa1eb6 fix(distributed): keep eviction inside the model's node selector

When no node the selector allows has a free slot, scheduling falls back
to evicting the least-recently-used idle model. That eviction searched
every healthy node, so it freed a slot on a node the selector forbids
and the model was then placed there: pinned to one class of hardware and
running on another.

An unrelated model pays for it. On this cluster an embedding model
pinned to Apple hardware could not reach its only matching node, so each
attempt evicted a large language model from an Nvidia node, failed to
start there anyway, and left the evicted model to reload. Repeated, that
reads as one replica bouncing between nodes.

Eviction is now restricted to the candidate set the selector produced.
With no selector the candidate set is nil and eviction stays global.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude Code:claude-opus-5 [golangci-lint]

2026-08-24 13:18:35 +00:00

application

fix(distributed): publish the revision a request actually carries

2026-08-24 09:05:52 +00:00

backend

fix(distributed): stamp config revision at load time

2026-08-23 14:35:44 +00:00

cli

fix(vram): persist remote probe metadata (#11487 )

2026-08-23 08:55:13 +02:00

clients

security(http): refuse redirects on outbound clients via hardened pkg/httpclient (#10087 )